Automated Marketing Research Using

Online Customer Reviews

Abstract

Market structure analysis is a basic pillar of marketing research. Classic challenges in

marketing such as pricing, campaign management, brand positioning, and new product
development are rooted in an analysis of product substitutes and complements in the marketplace
inferred from such structures.

In this paper, we present a method to support the analysis and visualization of market
structure by automatically eliciting product attributes, and brand’s relative positions, from online
customer reviews. First, we discover attributes and attribute dimensions using the "voice of the
consumer,” as reflected in customer reviews, rather than that of manufacturers. Second, the
approach runs automatically. Third, we support rather than supplant managerial judgment by
reinforcing or augmenting attributes and dimensions found through traditional surveys and focus
groups.

We test the approach on three different product domains: a rapidly evolving technology
market, a mature market, and a service good. We analyze and visualize results in several
different ways including comparisons to expert buying guides, a laboratory survey, and
Correspondence Analysis of automatically discovered attributes.

Key words: market structure analysis; online customer reviews; text mining

Electronic copy available at: http://ssrn.com/abstract=1649466

 2

INTRODUCTION

Marketing research, the set of methods to collect and draw inferences from market-level

customer and business information, have been the lifeblood of the field of marketing practice and

the focus of much academic research in the last 30+ years. Simply put, marketing research, the

methods that surround it, and the inferences derived from it, have put marketing as an academic

discipline and as a functional area within the firm “on the map”. From a practical perspective,

this has brought forward the “stalwarts and toolbox” of the marketing researcher including

methods such as: preference data collection via Conjoint Analysis (Green and Srinivasan 1978)

inferring market structure via multi-dimensional scaling (Elrod 1988; Elrod 1991; Elrod, Russell

et al. 2002), inferring market segments through clustering routines (DeSarbo, Howard et al.

1991), or simply understanding the sentiment and “voice of the customer” (Griffin and Hauser

1993). While these methods are here to stay, the radical changes wrought by the Internet and

user-generated media promise to fundamentally alter the data and collection methods that we use

to perform these methods.

In this paper, we propose to harness the growing body of free, unsolicited, user-generated

online content for automated market research. Specifically, we describe a novel text-mining

algorithm for analyzing online customer reviews to facilitate the analysis of market structure in

two ways. First, the Voice of the Consumer, as presented in user-generated comments, provides

a simple, principled approach to selecting product attributes for market structure analysis (we

also discuss their use for conjoint studies as well). Traditional methods, by contrast, rely upon a

pre-defined set of product attributes (external analysis) or ex-post interpretation of derived

dimensions from consumer surveys (internal analysis). Second, the preponderance of opinion as

Electronic copy available at: http://ssrn.com/abstract=1649466

 3

represented in the continuous stream of reviews over time provides practical input to augment

traditional approaches (such as surveys or focus groups) for conducting brand sentiment analysis,

and can be done (unlike traditional methods) continuously, automatically, very inexpensively,

and in real-time.

Our focus on market structure analysis is not by chance, but rather due to its centrality in

marketing practice and its fit with text mining of user-generated content. Analysis of market

structure is a key step in the design and development of new products as well as the repositioning

of existing products (Urban and Hauser 1993). Market structure analysis describes the

substitution and complementary relationships between the brands (alternatives) that define the

market (Elrod, Russell et al. 2002). In addition to descriptive modeling, market structure

analysis is used for predicting marketplace responses to changes such as pricing (Kamakura and

Russell 1989), marketing strategy (Erdem and Keane 1996), product design, and new product

introduction (Srivastava, Alpert et al. 1984). Hence, if automated in a fast, inexpensive way (as

described here), it can have significant impact on marketing research and the decisions that

emanate from it.

There is a long history of research in market structure analysis. Approaches vary by the

type of data analyzed (panel-level scanner data, aggregate sales, consumer survey response) and

by the analytic approach (Elrod, Russell et al. 2002). Internal methods, characterized by

Multidimensional Scaling (MDS), simultaneously induce a market structure and those product

attributes that define substitutes and complements. By contrast, external methods, characterized

by conjoint analysis, are dependent on the representation of a customer’s utility as an

agglomeration of preferences for a predetermined set of attributes and their underlying

dimensions. Regardless of the use of an internal or external approach, with few exceptions,
 4

approaches to market structure analysis begin with the same set of survey or transaction sales

data and assume that “all customers perceive all products the same way and differ only in their

evaluation of product attributes (Elrod, Russell et al. 2002).” Models that incorporate customer

uncertainty about product attributes (Erdem and Keane 1996) serve to highlight the colloquial

wisdom, “garbage in, garbage out.” Surprisingly, despite its importance, there is little extant

research to guide attribute selection for these methods (Wittink, Krishnamurthi et al. 1982).

There is literature on the sensitivity of conjoint results to changing attribute selection, omitting

an important attribute, level spacing, etc. (Green and Srinivasan 1978) but not much on how to

choose those attributes in the first place. We propose to fill this gap using automated analysis of

online customer reviews. Specifically, in this paper, we visualize market structure by using

correspondence analysis, a variant of multivariate data analysis used in external analysis but

apply it to product attributes mined from the “Voice of the Consumer” in an automated manner.

We note, however, that ours is by far not the first use of user-generated content or even

specifically online reviews for the purposes of marketing action. The impact of customer

reviews on consumer behavior has long been a source of study. A large body of work explores

how reviews reflect or shape a seller's reputation (Eliashberg and Shugan, 1997; Chevalier and

Mayzlin, 2003; Dellarocas, 2003; Ghose, Ipeirotis, et al, 2006). Other researchers have studied

the implications of customer reviews for marketing strategy (Chen and Xie 2004). To stress its

importance and ubiquitous nature, a 2009 conference co-sponsored by the Marketing Science

Institute and the Wharton Interactive Media Initiative had over 50+ applicants all doing work on

user-generated content.

With that said, there has been comparatively little work on what marketers might learn

from customer reviews for purposes of studying market structure. Early work combining
 5

marketing and text mining focused on limited sets of attributes for purposes of analyzing price

premiums associated with specific characteristics (Archak, Ghose et al. 2007; Ghose and

Ipeirotis 2008; Ghose, Ipeirotis et al. 2009). By comparison, our objective is to learn the full

range of product attributes and attribute dimensions voiced in product reviews and to reflect that

in a visualization of market structure that can be used for marketing actions. Work that analyzes

online text to identify market competitors (Pant and Sheng 2009) focuses on the corporate level

and relies upon network linkages between Web pages and online news. Social networks have

also been used to segment customers for planning marketing campaigns, but relies upon directly

observable relationships between individuals (e.g. friends-and-family calling plans) with no

reference to user-generated comments (Hill, Provost et al. 2006). In this paper, we focus on the

product-brand level using user-generated product reviews.

Most recently, researchers have applied natural language processing (NLP) to

automatically extract and visualize direct comparative relationships between product brands from

online blogs (Feldman, Fresko et al. 2007; Feldman, Fresko et al. 2008). Our work is

complementary in at least three ways. First, we present a simpler set of text-mining techniques

that is less dependent upon complex language processing and hand-coded parsing rules, requires

minimal human intervention (only in the analysis phase), and is better suited to customer reviews

(Hu and Liu 2004; Lee 2005). Second, our focus is on learning attributes as well as their

underlying dimensions and levels. Our goal in learning attributes, dimensions and levels is not

only to facilitate direct analysis but also to inform more traditional market structure and conjoint

analysis methods. Third, we specifically highlight the “Voice of the Consumer”. Different

customer segments such as residential home users of personal computers versus hard core

gamers may refer to the same product attribute(s) using different terminology (Randall,
 6

Terwiesch et al. 2007). These subtle differences in vocabulary may prove particularly useful in

identifying unique submarkets (Urban, Johnson et al. 1984).

Therefore, to summarize, we present a novel combination of existing text-mining and

marketing methodologies to expand the traditional scope of market structure analysis. We

describe an automated process for identifying and analyzing online product reviews that is easily

repeatable over reviews for both physical products and services and requires minimal

human/managerial intervention. The process extends traditional market structure analysis in the

following ways:

 Provides a principled approach for selecting attributes for market structure analysis by

identifying what attributes customers are commenting on as well as the polarity of those

comments (positive v. negative).

 Identifies not only what attributes customers are speaking about but also how they speak

about it. In particular, our approach identifies not only attributes but elicits underlying

attribute dimensions as well as value levels for those dimensions.

 Highlights the Voice of the Consumer. We can think of how a customer describes

product attributes not only in terms of attribute dimensions and levels but also in terms of

vocabulary (West, Brown et al. 1996). Both differences in granularity (dimensions and

levels) and differences in vocabulary can signal differences between consumer segments.

 Discovers attributes within user-generated comments that are not highlighted using more

traditional techniques for eliciting attributes and dimensions such as those used to

construct expert buying guides. As an example, we found “missing” attributes

discovered within our approach that are meaningful as determined in a follow-up survey

conducted to assess the degree to which these attributes were important to consumers.
 7

 Facilitates market structure analysis over time by enabling the periodic (re)estimation of

market structure through discrete sampling of the continuous stream of reviews.

 Supports rather than supplants traditional internal (perceptual mapping) and external

(conjoint analysis) approaches for market structure analysis by suggesting attributes and

dimensions in addition to those that emerge from traditional focus groups and surveys.

 Possesses high face validity in attribute and dimension selection for practical significance

because marketing managers are familiar with and have easy access to online reviews.

In the remainder of this paper, we provide an overview of our technical approach, revisit the

approach in detail, and analyze and evaluate the approach on three different product domains.

OVERVIEW

Our approach is summarized in Figure 1. We review the entire process here in an

“informal heuristic way” as many of these techniques are new to the marketing audience; we

then revisit each step in greater detail later for those who would like to replicate our approach.

The process begins with a set of online reviews in a product category over a specified time

frame. For example, in this paper, we consider the reviews for all digital cameras available at

Epinions.com as of July 5, 2004. Figure 1, Step 1 shows three reviews, one for a camera

manufactured by Olympus, one for a camera by HP (Hewlett Packard), and one for a camera by

Fuji. In Step 2, screen scraping software automatically extracts details from each review

including the brand and a list of Pros and a list of Cons. Our goal is to group all phrases

discussing a common attribute into one or more clusters to reveal what customers are saying
 8

about the product space and how they say it. While some review sites do not provide user-

authored Pro and Con summaries (e.g. Amazon.com), many others including Epinions.com,

BizRate, and CNet do (Hu and Liu 2004). Exploiting the structure provided by Pro and Con lists

allows us to avoid numerous complexities and limitations of automated language processing

from prose-like text. This allows us to have our process be “automated”, whereas extant

research less so.

All of the Pros and Cons are then separated into individual phrases as depicted in column

1 of the table in Figure 1, Step 3. Preprocessing transforms the phrases from column 1 into a

normalized form. Column 2 depicts one step of pre-processing, the elimination of uninformative

stop-words such as articles (“the”) and prepositions (“of”). Each phrase is then rendered as a

word vector. The matrix of word vectors is depicted in the remaining columns of the table in

Step 3. Each row is the vector for one phrase. Each vector index represents a word and the

vector value records a weighted, normalized count of the number of times that the indexed word

appears in the corresponding phrase. Additional details are below.

Phrases are automatically grouped together based upon their similarity. Similarity is

measured as the cosine angular distance between word vectors and is identical to the Hamming

distance used in computer-science based research. Step 4 depicts the K-means (albeit other

algorithms can be easily used) clustering of the phrases from Step 1. Conceptually, we may

think of each cluster representing a different product attribute. The example shows clusters for

“zoom,” “battery life,” “picture quality,” and “memory.”

In product design, a product architecture defines the hierarchical decomposition of a

product into components (Ulrich and Eppinger 2003). In the same way, Step 5 depicts the

hierarchical decomposition of a product attribute into its constituent dimensions (i.e. attribute
 9

levels a la conjoint analysis). In Step 5a, we show a conceptual decomposition of the digital

camera product attribute “memory.” In Step 5b, we show an actual decomposition using only

the phrases from Step 1. The decomposition is treated as a linear programming assignment

problem (Hillier and Lieberman 2001). The objective is to assign each word in the attribute

cluster to an attribute dimension. Each word phrase defines a constraint on the assignment: any

two words that co-occur in the same phrase cannot be assigned to the same attribute dimension.

Thus, we know that “smart” and “media” cannot appear as a value for the attribute dimension

quantity (4, 8, 16) or for the attribute dimension of memory unit (“mb”). Note that not all

phrases include a word for every dimension. Intuitively, this is both reasonable and an important

aspect of capturing the Voice of the Consumer. We wish to know not only what customers say

but also how (at what level of detail) they say it. For the algorithm, phrases that do not include a

word for each attribute simply represent a smaller set of co-occurrence constraints than a phrase

containing more words.

[Insert Figure 1 about here]

DETAILED DECRIPTION OF APPROACH

In this section we revisit various steps in the process described above in greater detail.

Specific algorithms and pseudo-code describing the implementation appear as an appendix and

the code is available from the authors upon request.

Steps 1 and 2: Choosing products and data extraction

 10

Step1 simply involves identifying a source for reviews and identifying the product (or set

of products) that we wish to analyze. For Step 2, we wrote a program in the Python

programming language. For each review, we get the product identifier used by Epinions.com to

uniquely identify a product, the list of Pros, and the list of Cons. Product brand names are

excerpted from the Epinions.com product identifier1 and inserted into a MySQL database. It is

also important to note that one could separate the selected reviews by pre-defined segments (i.e.

demographic clusters, and hence produce segment-level Pro-Con lists that would be analyzed

distinctly), or attempt to (but is beyond the scope of this research) to simultaneously infer latent

segments and market structure simultaneously.

Step 3. Word vectors

To construct the matrix of word vectors, we focus on each phrase. For now, we do not

distinguish between whether a phrase appears as a Pro or a Con, focusing only on grouping

together those phrases that discuss a common product attribute. Later, we will see whether

looking at Pros versus Cons separately provides differentiated market structure, an important

idea in that marketing managers may be interested in understanding market structure on the

“positive side” versus market structure on the “negative side” (i.e. we have the pluses of our

competitors but don’t share their negatives). As a standard preprocessing step in text mining,

we normalize words as follows. Delete all stop-words and stem the remaining text (Salton and

McGill 1983). Stop-words, like grammatical articles, conjunctions, prepositions, etc. are

meaningless for purposes of product attribute identification so they are removed. For example,

after pruning, the phrase "Only 8 mb Smart media card included" becomes "8 mb Smart media

card included." Reduce words to their root form by stemming. We use the Porter stemmer to
 11

find equivalences between singular, plural, past and present tense forms of individual words used

by customers. Thus, "includes" and included" are both reduced to the root "includ."

Formally, i = 1, …, I indexes phrases and j = 1, …, J indexes over every word in the

review space so that the word vector for every phrase, taken together, form a matrix. Every entry

in the matrix(i,j) measures the importance of a word j in characterizing or defining the product

attribute discussed by phrase i. Every row of the matrix represents the corresponding phrase in

the vector space of words. The matrix values for each word are based upon word frequency and

derived from the TF-IDF (Term Frequency-Inverse Document Frequency) standard (Salton and

McGill 1983). Specifically, terms describing product attributes and sentiments tend to exhibit

unusually high frequencies in reviews. By considering reviews from unrelated product domains

(to form a control condition, i.e. a null importance matrix), we extend the TF-IDF measure to

distinguish words describing product-specific attributes from sentiment words. Details on

calculating word importance appear in Appendix 1.1.

Step 4. Clustering phrases

Intuitively, our objective is now to cluster the vectors (the matrix rows) so that all phrases

describing the same product attribute are grouped together. More formally, given the phrase 

word matrix(i,j) over the set of I phrases and the set of words J, we seek to separate phrases into

a set C of k mutually exclusive and exhaustive clusters We use the cosine measure of angular

distance between vectors to calculate similarity. The cosine measure is then applied to the

phrase  word matrix using the K-means clustering algorithm. While any number of clustering

algorithms is acceptable, we selected K-means for its simplicity and its familiarity to both the

text-mining and marketing communities. More complex topic clustering algorithms like
 12

Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Analysis (LDA) also require

parameter estimation and marketing approaches such as Latent Structure MDS (LSMDS) begin

with a pre-defined set of product attributes. As noted earlier, the principle contribution of our

work is the elicitation of product attributes directly from the customer.

The quality, QC, of a K-means clustering, C, is calculated by the sum of the distances

from each vector in a cluster to that vector's centroid. Following (Zhao and Karypis 2002), this

metric is more simply defined as the sum of the length of the composite vectors:

QC    cosv, centroid c    compositec 

ci C vci
i
ci C
i

where compositeci   v (1)

vci

Because K-means is known to be extremely sensitive to its initial conditions, we repeat the

algorithm ten times, beginning with a new, random set of k centers and pick the solution that

maximizes QC.

Step 5. Attributes and their dimensions

A critical step in our approach is to discover not only what product attributes customers

are discussing but also how they say it. More particularly, we answer the question of how by

discovering the attribute dimensions that customers use in their reviews. To discover attributes,

we assume that each phrase corresponds to a distinct product attribute. To discover attribute

dimensions, we will assume that each word in the phrase corresponds to a distinct dimension.

Discovering attributes then reduces to the assignment of particular words to attribute dimensions.

Conceptually, we model this process as a constrained optimization problem. Abusing our

previous notation slightly, assume a set of phrases I composed from the set of words J and a set
 13

of attribute dimensions D. We have J  D binary decision variables Xjd where Xjd is 1 if word j

is assigned to dimension d. There are I  J {0, 1} variables representing a constraint matrix

where Yij is 1 or 0 depending upon whether word j appears in phrase i. Thus, our objective is to:

max  X jd
s.t. i  J Yij * X jd  1
X jd binary

The graph partitioning algorithm used to set the parameters I, J, and D and the

constrained logic program (CLP) by which we solve the optimization are implemented in Python

and detailed in Appendix 1.2 and 1.3 respectively. Logical assignment is depicted in Table 1. A

maximal clique (see appendix) appears in the top row, the constraints represented by phrases of

normalized words appear in the middle column, and the corresponding assignment appears in the

columns to the right.

[Insert Table 1 about here]

ANALYSIS AND EVALUATION

There are at least two ways of evaluating the quality and efficacy of approaches such as

ours. For a given product, we can “objectively” compare attributes that are automatically

discovered from customer reviews to an external reference standard (e.g. Consumer Reports).

Alternatively, and more directly, we can visualize and analyze the results by using the attributes

to map the relationship between competitors in the marketplace (i.e. the construction of a market

structure map). In this section, we do both and report results from the application of our

approach to an actual set of digital camera product reviews. We then ask how the results change:
 14

if we consider only positive or negative comments, when we look at reviews over different time

periods, using just pros or cons, and apply the process to two additional product domains to

demonstrate its breadth. Finally, we explore a natural accompaniment to internal market

structure analysis and consider the extension of our approach to conjoint analysis, an external

market structure approach (Elrod, Russell et al. 2002).

Digital cameras

Our initial data set consists of 8,226 online digital camera reviews downloaded from

Epinions.com on July 5, 2004. The reviews span 575 different products and product bundles that

range in price from $45 to more than $1000. Parsing the Pro and Con lists produces the

aforementioned phrase  word matrix that is 14,081 phrases by 3,364 words. We first set k (the

number of maximum clusters for K-means) at 50 by analyzing the set of all product attributes in

our reference buying guides in a manner that follows Popescu et al. (2004). While relying upon

experts is common, there are also a number of more general, statistical approaches for initializing

k including the Gap (Tibshirani, Walther et al. 2005) and KL (Krzanowski and Lai 1988)

statistics. Because of its computational simplicity, we plotted k versus KL in a range from 45 to

55 and found that k maximizes the value of KL at 50. Setting k = 50, we iterated K-means

clustering 10 times, selecting the best resulting output based upon QC (Eqn 1).

Given an initial set of 50 clusters (from K-means), our next step is to further filter the

initial clusters into attribute dimensions. The CLP process produced a total of 171 sub-clusters

describing attributes and dimensions within the 50 initial clusters. Applying a χ2 threshold of

.001 and further filtering the results using the Spearman Rank test rs (see Appendix 1.3) reduces

those 171 sub-clusters to 99. Within each cluster, sub-clusters may represent noise from K-
 15

means or different ways in which customers express the dimensions of an attribute (e.g. the

number of batteries, the type of batteries, or battery life). To this point, the entire research

process is fully automated with no human intervention whatsoever. Finally, a manual reading

reveals which of the remaining sub-clusters discuss a common product attribute, and which are

noise; albeit, in the future even this could be automated. Our final reading identifies 39 clusters

of product attributes (see Table 2). Though we might have expected 50 sub-clusters, one for

each of the initial clusters, this is not the case. For some initial clusters, none of the sub-clusters

pass the statistical filters. In other cases, multiple sub-clusters within a single cluster may

indicate that the parent cluster does not cleanly distinguish a common product attribute.

To facilitate the presentation, we apply a naïve convention for naming each cluster (a

common practice in marketing studies): scan the cluster for the most frequent word(s) in each

cluster. Some resulting cluster names may only have meaning in the product context.

Comments are inserted in parentheses to provide context to the automatically generated name as

well as to indicate where certain product attributes are duplicated. A listing of automatically

generated dimensions for each of the 39 attributes is available in a separate appendix available

from the authors.

[Insert Table 2 about here.]

Comparison to expert buying guides

As an objective measure of the success of our approach, we compare attributes and levels

derived from our online customer reviews to those discovered using more traditional measures

such as those used in creating expert buying guides. In particular, we compute (P) (Salton and

McGill 1983) the number of automatically generated attributes and dimensions also used by
 16

experts in published buying guides. Conversely, recall (R) counts the number of attributes and

levels named in professional buying guides that are automatically discovered in the Voice of the

Consumer. More formally, if X is the set of attributes from the Voice of the Consumer and Y is

the set of set of attributes identified in professional guides, P and R are defined as:

X Y X Y
P and R 
X Y

The first three columns of Table 3 describe the reference sources. Epinions (A)

represents the attributes and levels by which customers can browse the digital camera product

mix and Epinions (B) represents a buying guide available on the Epinions website. CR02 –

CR05 represent print buying guides regarding digital cameras from Consumer Reports for the

years 2002 through 2005. The next two columns report precision and recall where reference

attributes must exactly match an automatically generated cluster from our approach.

Exact matching is an aggressive standard in comparing hierarchies. “Optical zoom” is an

attribute in some reference guides while the automatic process identified “optical” as a

dimension of “zoom.” Borrowing from Popescu et al. (Popescu, Yates et al. 2004), we further

define precision and recall containment (P+ and R+) to allow specific terms to qualify as a

match for more general terms, provided that the more specific term appears as a dimension or

level, and vice versa. In the final two columns, we report P+ and R+.

[Insert Table 3 about here]

A quick review suggests that the automated extraction performs with varying quality

relative to the on-line buying guides. Given that different sources may be subject to different

biases and that technologies evolve over time, we also considered all pairwise comparisons
 17

between the reference guides themselves. Table 4 reports the average precision and recall from

evaluating each external source against every other one.

[Insert Table 4 about here]

The results suggest, at least in part, that the external sources are neither exhaustive nor

even consistent with one another. Hence, a more appropriate benchmark for evaluation may be

the internal consistency between the sources themselves. Assuming containment, the .72

average recall from our approach, labeled "Auto" in Table 4, exceeds all others. At the same

time, the precision is equal to the median consistency among all guides. As generating a "larger"

list automatically can be further reduced by post-time human intervention, such results are both

encouragingly supportive of our approach and suggests its’ potential use.

Most importantly, our attributes come directly from customer reviews. In some cases,

our product attributes may not closely align with those in the marketing materials for

manufacturers and retailers. Our results therefore suggest that product reviews do reveal

information not used in the traditional methods. The managerial question is therefore not

whether online product reviews provide information; but instead, the question is what value that

information provides. Did we find “unseen” important attributes? We discuss that next.

Objective comparison to user surveys

To assess the value of our automated process, we conducted a laboratory survey that

asked subjects to evaluate the importance of different attributes for the purpose of purchasing a

new digital camera. We find that automated analysis of online product reviews can support

managerial decision-making in at least two ways. First, our approach can identify significant

attributes that are otherwise overlooked by the experts. Second, the reviews can serve as a filter
 18

for other attribute elicitation methods; attributes that are identified by experts but also named by

customers may have more salience for purposes of product marketing and design.

Specifically, our survey, which took less than 5 minutes to complete, was administered as

part of a 60 to 90 minute sequence of experiments where subjects were compensated at the

average rate of $10/hour. Pre-testing suggested no interference between our survey and the

unrelated studies conducted during the same session. In total, 181 subjects at a large

Northeastern university participated in our web-based survey. Based upon validity checks and

response times, results were obtained for 164 subjects.

A set of product attributes for testing was constructed by reconciling the 39 attributes

shown in Table 2 with all of the attributes identified in the 10 different reference buying guides

listed in Table 3. After duplicate attributes were eliminated, the resulting set of 55 attributes was

divided into overlapping thirds to reduce any individual respondent’s burden. See Appendix 3

for the complete list. A few attributes were repeated in each third as an additional validity check.

Each subject viewed between 20 and 21 attributes. Subjects were asked to rate their "familiarity

with" and the "importance of" each attribute using a 1- 7 scale. The specific questions were:

Imagine that you are about to buy a new digital camera. In the table below, we give a

list of camera attributes. For each attribute, please answer two questions:

First, from 1 – 7, please rate how familiar you are with the attribute. [1] means that you

have no idea what this attribute is and a [7] means that you know exactly what this is.

Second, from 1 – 7, please rate how much you care about this attribute when thinking

about buying a new digital camera. [1] means that you do not care about this attribute at all
 19

and [7] means that this is critical. You would not think of buying without first asking about this

attribute.

Subjects were prompted to answer all questions. In particular, subjects were reminded to

answer the second question for each attribute even if they answered [1] for the first question. In

Part 2 of the survey, to understand the role that expertise might play, subjects were asked to

provide their self-assessed expertise on digital cameras (1= “novice” and 7 = “expert”).2 Finally,

subjects were asked for a standard set of demographic variables such as age, gender, education-

level, etc. These variables were used as covariates to verify our main findings.

Our main results are summarized in Figure 2 where we plot the mean familiarity versus

mean importance for each of the 55 attributes. Attributes that appeared only in one or more

buying guides are labeled "Expert Only" and symbolized by diamonds. Attributes that appear in

at least one buying guide and also in our automated results are labeled "Expert + VOC (Voice of

the Consumer)" and are identified by squares. Finally, attributes that emerged only from our

automated analysis of reviews are labeled "VOC Only" and plotted as "X" symbols. As we

would expect, the graph indicates a general trend upwards and to the right. Users are more

familiar with those product attributes that they tend to consider important. Similarly, if a user is

unfamiliar with a particular attribute, they are unlikely to place a high value on that attribute. A

complete table of attributes and their respective familiarity and importance means is provided in

Appendix 3. We note that, in general, "importance" does not vary greatly by gender, expertise,

or any other demographic variable. In several instances, whether the subject owns a digital

camera does exhibit some significance. The significance of covariates should be checked

separately in each applied domain.

 20

Figure 2 suggests two significant managerial implications. First, there are eight attributes

labeled "VOC Only," and they tend towards the upper right-hand corner of the plot: (camera)

size, body (design), (computer) download, feel (durability), instructions, lcd (brightness), shutter

lag, and a cover (twist lcd for protection). The existence of product attributes that are both

familiar and important to users suggests the value of processing online reviews to augment

existing methods for identifying salient product attributes.

[Insert Figure 2. about here]

Moreover, by comparing the "Expert Only" plot to the "Expert + VOC" label in Figure 2,

we see that most high-importance, high-familiarity attributes appear as "Expert + VOC" while

the lower-left hand region is populated primarily by "Expert Only" attributes. Comparing the

"Expert Only" attributes to "Expert + VOC" attributes, we find a statistically significant

difference (p < .01) in average familiarity (4.2 to 5.1) and in average importance (4.1 to 4.9).

The difference (p < .05) between "Expert Only" and "VOC Only" is equally large and suggests a

second managerial application of automated analysis. The "Voice of the Consumer" as

represented in online product reviews can serve as a filter, highlighting meaningful product

attributes.

The potential for applying "VOC" as a filter is also seen in the wide disagreement among

the Expert Buying Guides. There are only seven product attributes that appear in at least 50%

(five) of the Expert guides used in our evaluation. Labeled by "+" symbols in Figure 2, we see

that even when the Experts agree, there is a wide variance in familiarity and importance that is

mediated by the "VOC."

 21

At the same time, it is worth noting that our procedure does miss some high value

attributes. In particular, two sub-classes of attributes stand-out. "Brand" is certainly a prominent

missing attribute. Our approach relies on word frequencies. Specific references to any one

brand (e.g. “Canon”) may not appear with sufficient frequency to cluster as an attribute. We

might instead map all explicit brand names to a single common word (e.g. “brand”).

The second sub-class of attributes missed by our approach is largely due to differences in

how terms are classified. In Figure 2, the attribute ranked second in importance among "Guide

Only" results is "battery source." While our automated approach does capture characteristics of

batteries and even battery type, these values are classified as properties of the "battery" attribute.

Likewise, we distinguish between “shutter lag” and “shutter delay.” Although the terms refer to

the same physical characteristic, distinctions in vocabulary may reveal distinct submarkets. In

this way, our analysis highlights differences between the voice-of-the-consumer as represented in

product reviews with that of the manufacturer and retailer’s marketing literature.

Visualizing the market space

In addition to identifying the salient attributes, we further utilize the extracted

information to understand and visualize market structure. A product brand is associated with

each online review. Using the automatically generated attribute clusters, we generate a brand by

attribute matrix, counting the number of brand occurrences (number of phrases) for each attribute

and, as standard, normalized by the total number of phrases for that brand. To then turn this into

a visual “map”, we utilize Correspondence Analysis. Correspondence Analysis (CA) is a

technique for analyzing two-way, two-mode frequency data (Everitt and Dunn 2001) making it

more appropriate for this task than continuously scaled MDS procedures that are commonly used
 22

for market structure map construction. CA is designed to help generate hypotheses by

representing the data in a reduced space as measured by consulting the eigenvalues and the

corresponding scree plot (Greenacre 1992). To help interpret the dimensions in the reduced

space, we use (stepwise) regression of each brand’s (x,y) coordinates on the derived attributes.

The probability for entry is 0.05 and probability for removal is 0.1, albeit other values were

tested and yielded high robustness.

Figure 3 depicts the brand map in two dimensions based upon the initial set of digital

camera reviews analyzed for this study alongside the Scree plot of the eigenvalues and

cumulative percentage of inertia. In the paper, the visualizations are limited to two dimensions.

However, we recognize that the reliability of any such model is dependent upon fit as

represented by the percentage of inertia captured by those dimensions. At the limit, we imagine

that marketing managers might use the two-dimensional figures as a point of departure for

interpretation with respect to decision-making.

The percentages on the axes indicate the percentage of inertia for F1 and F2 respectively.

The isolation of Casio in the lower right quadrant of the coordinate axes and the positioning of

Panasonic as farthest from the origin or “average” representation in the dimensional space are

consistent with the empirical data. Of the nine brands in the brand map, only Casio and

Panasonic are not represented in the 20 best-selling digital cameras of 2004 (InfoFaq) and the

“Best of 2004” as documented by the Digital Imaging Website Association.

[Insert Figure 3 about here]

Following convention, we rescale the axes and plot both brands and attributes in the same

space in Figure 4. Only A20, about “slow” or “fast” startup, boot-up, or shut down, appears in

the lower right quadrant perhaps explaining Casio’s isolation. Furthermore, attributes A18 and
 23

A21 appear in the upper left quadrant. This suggests that “AC power adapters” and the camera’s

“body construction” are not relevant to customers when evaluating brand (dis)similarity. For the

marketing manager, this provides several initial hypotheses for improving or repositioning

Casio’s product while exploring additional opportunities for differentiation.

[Insert Figure 4 about here]

Regressing the CA coordinates (F1 and F2) on the attribute clusters defines F1 as a

combination of comments about camera options (e.g. manual focus, auto focus, aperture) and

slow startup/shutter delay. F2 captures some combination of camera size (e.g. easily fits into a

pocket or hand) and external memory cards (e.g. SD card, Compact Flash, etc.). A summary of

the stepwise results for variable selection are included as an appendix. An alternative approach

to naming the dimensions would have been to regress on the actual, manufacturer-provided

physical dimensions. However, this is exactly what makes our approach novel/different. Figure

3 is unique in that it reflects perceptions as revealed through automated analysis of customer

reviews and not manufacturer specifications.

One additional benefit of using structured Pro-Con lists is the ability to immediately

identify the sentiment polarity (Pro phrases convey positive polarity and Con phrases convey

negative polarity). Beginning with the attributes derived from clustering review phrases, we

label each cluster based upon whether it includes only Pro phrases, only Con phrases, or both.

We construct the combined Pro-Con dimensional space by considering attributes that comprise

the intersection (attributes that are mentioned as both Pro and Con) or the union of all attributes.

In Figure 5, we drill down on brand differences by explicitly considering the polarity

with which comments are made in constructing our market structure map. Because there was
 24

little qualitative difference in the relative positioning of brands between using the intersection of

Pro and Con attributes versus the union of Pro and Con attributes, we depict only the union.

[Insert Figure 5 about here]

As one would expect, in the combined space, there is a clear separation between Pro and

Con phrases. As stated earlier, this provides another layer of insight into brand positioning:

“Who are our competitors on the praise dimensions and criticism dimensions?” To the best of

our knowledge, this is a further unique contribution of this research that has never been explored.

Interestingly, Casio’s brand isolation exists only in the context of Pro comments, perhaps

suggesting that the differentiation is not due to an inferior product. Rotational distinctions aside,

we see that most brands retain a close relative positioning between Pro and Con with respect to

the average (or origin) in the combined space. By contrast, Sony is clearly further away with

respect to negative comments suggesting the need for their further exploration. In the interest of

space and readability, we omit the figure projecting attributes and brands in the same figure.

However, the regressions suggests that F1 is best explained by a combination of “slow” or “fast”

startup, boot-up, or shut down, controls (e.g. white balance, etc.), and the viewfinder. F2 is

explained by remarks about the LCD, about reliability and service, and about battery life.

Robustness and changes over time

Polarity aside, another benefit of automatically analyzing user-generated content is the

ability to map changes in the environment over time in real-time. For the marketing manager,

customer reviews offer an opportunity to measure the impact and diffusion of campagins as

reflected in the Voice of the Consumer. Conversely, as noted earlier, tapping reviews offers a

way of aligning a campaign with the vocabulary of the target market.

 25

We collected a parallel set of 5567 digital camera reviews from Epinions.com dated

between January 1, 2005 and January 28, 2008. The new set of reviews produced 39 initial

attribute clusters. After accounting for duplicates (e.g. multiple clusters referring to resolution),

there were a total of 30 unique digital camera product attributes. Five new attributes were

surfaced replacing five previously formed clusters. The substitutions are listed in Table 5.

Although it is difficult to discern the underlying causes, the changes have face validity. As the

customer base becomes increasingly sophisticated and increasingly connected online, the need

for instructions and support has shifted towards online self-service. Likewise, the ubiquity of

personal computers and online photo management software may have shifted such functions

away from the camera. In keeping with the theme of a more technically sophisticated audience,

functions such as ISO settings, multiple shot modes, and white/color balance are more significant

or reflect active campaigns.

[Insert Table 5 about here]

Even though many attributes remain the same across time periods, changes in both

customers and the marketplace may drive (or reflect) brand repositioning over time. To

construct a combined attribute space over two time periods, there are at least two approaches.

The first is to cluster reviews from each time period independently, derive attribute clusters for

each period, and then construct the combined space from attributes appearing in both periods

(intersection) or from either period assigning zero counts to brands in the time period where the

attribute does not appear (union). Manual intervention is required to align clusters from the

different periods to ensure that they reference the same items. A more automated approach, as

with our combined Pro-Con space, would cluster reviews from both time periods together. Each

attribute cluster is then labeled depending upon whether it includes phrases from period 1, from
 26

period 2, or from both. The combined space could again include the intersection or union of

attributes. To minimize the amount of human intervention required in our process, we pursued

the second strategy. For example, Figure 6 depicts changes in brand positioning over time with

respect to positive (Pro) customer comments. Because there was little change in the

visualization of relative brand positioning when using intersection or union in the combined

space, we only depict the union.

[Insert Figure 6 about here]

Figure 6 depicts a clear trend with brands converging towards the origin, which is entirely

expected. In a fast moving market marked by innovation and new product introduction, one

would expect a degree of convergence as manufacturers attempt to follow one another. The

exception is Panasonic, which is notable in that it moved away from the other brands.

Robustness and additional domains

We also explored the robustness of our approach by applying the technique to two

additional product/service domains. Because we consider digital cameras to be an evolving,

technology sophisticated product domain, we first considered a more stable product domain:

Toaster ovens.

We downloaded all Epinions.com toaster oven reviews available on 10/5/2007 and split

the data set as of January 1, 2005. Before 2005, there are 402 reviews, and after, there are 398

reviews. Product prices range from $20 to $380. Maximizing KL set the number of clusters (k)

at 25. After filtering the clusters, the resulting 18 attributes (including duplicates) are listed in

Table 6.

[Insert Table 6 about here]

 27

In Figure 7, we map the market structure for Toaster Ovens. F1 is explained by “(lack

of) reliability,” “ease of access to interior (for cleaning or inserting/removing food),” and “toast.”

F2 is explained by “browning (cooking method),” “ease of access,” and “reviews (what others

say, suggest, or have read).” In a mature market, one might expect greater stability over time.

The CA plot does show some convergence. Hamilton, Cuisinart, Oster appear to move towards

the origin. Other brands like Toastmaster and Krups, move counter to that trend while others

(DeLonghi or Black and Decker) show little relative movement. Such activity is consistent with

the opportunity to innovate even in seemingly staid markets (Urban, Johnson et al. 1984; Urban

and Hauser 1993) but less so than what we observed for digital cameras.

[Insert Figure 7 about here]

For the second domain, we studied a single set of 3800 hotel reviews from Philadelphia,

Houston, and Washington, DC downloaded from TripAdvisor.com on June 8, 2009.

Maximizing KL and then filtering resulted in the 34 attributes (including some duplicates) in

Table 7. When describing attributes of services, customers may write in ways less amenable to

traditional NLP sentiment analysis (Pang and Lee 2008). Comments about service attributes and

dimensions may also prove less quantifiable or readily actionable (e.g. “staff friendliness”).

Consequently, work applying text and data mining to hotel reviews tends to exploit a pre-defined

set of amenities from hotel descriptions and/or limit the text mining to measures of readability

and subjectivity (Ghose, Ipeirotis et al. 2009). Our work, by contrast, uses the customer reviews.

[Insert Table 7 about here]

We again used CA to visualize the market structure. When looking at digital cameras,

many different camera models were aggregated within a single brand name. For hotels, we

drilled down on brands to distinguish between distinct sub-markets within and between hotel
 28

chains. Figure 8 looks only at positive comments. Despite attempts to draw distinctions

between sub-markets, it is interesting to see that distinct brand clusters may or may not emerge.

In Figure 8, F1 corresponds to room size and amenities, breakfast and other food and dining

resources, and the bed. F2 corresponds to price, location, and parking. Only the Limited Service

hotels are in the lower right quadrant. Full Service hotels primarily cluster above the X axis.

Interestingly, where more than one hotel brand is available, the parent company (Hilton,

Starwood, Holiday Inn, and Marriott) distributes its presence across the different quadrants of the

CA space, targeting distinct market segments.

[Insert Figure 8 about here]

The market space is plotted with respect to negative comments in Figure 9. Again, the

intention is not to definitively define the market structure. Rather, our goal is to suggest that, on

its face, analyzing consumer reviews can reveal not only attributes (what people discuss) but the

actual Voice of the Consumer (how they discuss it). Such distinctions may offer a unique

opportunity to analyze the evolution of market structure from the perspective of customer

perceptions as expressed in their own voice.

[Insert Figure 9 about here]

External market structure analysis and conjoint

In contrast to CA and internal market structure analysis, Conjoint Analysis is perhaps the

most common approach to external market structure analysis (Elrod, Russell et al. 2002). We

might envision the (re)design of conjoint studies based upon attributes defined by the Voice of

the Consumer. Conjoint studies have been applied to new product introduction (Wittink and

Cattin 1989; Michalek, Feinberg et al. 2005), optimal product repositioning (Moore, Louviere et

al. 1999) and pricing (Goldberg, Green et al. 1984), and segmenting customers (Green and
 29

Krieger 1991). However, conjoint is dependent on the representation of a customer’s utility as

an agglomeration of preferences for the underlying attribute levels that have been selected. This

dependence holds regardless of either format (choice-based, ratings-based, ranking-based,

constant sum, or self-explicated) or method for determining the profiles (Huber and Zwerina

1996; Moore, Gray-Lee et al. 1998; Toubia, Simester et al. 2003; Evgeniou, Boussios et al.

2005).

The automated analysis of online product reviews could potentially assist in the design of

conjoint studies in at least three ways. First, as previously noted, customer reviews may reveal

attributes not included elsewhere. Second, reviews reveal not only what customers speak of but

how they speak about it. Analysis of reviews can help inform the granularity with which

atributes are described and the vocabulary used to describe those attributes. Finally, analysis of

reviews can help produce meaningful levels for conjoint study design.

Our approach for revealing attribute dimensions (as described in Table 1) assigns words

to individual attribute dimensions. For example, “3x,” “4x”, “5x”, etc. might all be assigned to a

single attribute dimension for zoom “magnification.” Using techniques such as distributional

clustering (Pereira, Tishby et al. 1993), we can group words within the cluster of an attribute

dimension to meet a managerially specified target number of levels (Lehmann, Gupta et al.

1997). The result is a conjoint study designed by customers, in the words of customers, for

prospective customers. Our hope is that this research brings one of the key conjoint open issues

to receive further attention.

DISCUSSION AND CONCLUSIONS

 30

In this paper, we have presented a system for automatically processing the text from

online customer reviews. Phrases are parsed from the original text. The phrases are then

normalized and clustered. A novel logical assignment approach exploits the structure of Pro-Con

review summaries to further separate phrases into sub-clusters and then assigns individual words

to unique categories. Notably, our work differs from sentiment-based strategies in that we do not

rely upon complex natural language processing techniques and do not rely upon the user to first

provide a set of representative examples or keywords (Turney 2002 ; Nasukawa and Yi 2003; Hu

and Liu 2004; 2006). However, opportunities to refine our approach are symptomatic of broader

conceptual and pragmatic issues discussed briefly next.

Conceptual considerations

To generate initial clusters, the system requires phrases. Even though Epinions' customer

reviews provide lists of phrases, variations in human input are a source of noise. Moreover, we

assume that a phrase represents a single concept and that individual words represent distinct

levels of attribute dimensions. It is easily seen how this assumption creates difficulties with the

natural language in reviews (e.g. people who write lists like "digital and optical zoom").

One possible solution is to apply more sophisticated NLP techniques. Beginning with a

representative set of meaningful words, there are ways of expanding the set of words,

distinguishing between distinct attributes, and identifying relationships between attributes

(Hearst 1992; Maedche and Staab 2000; Popescu, Yates et al. 2004; Popescu and Etzioni 2005).

However, our Pro-Con summaries are simply lists of phrases with no associated linguistic

context; Liu et al. (2005) demonstrate that techniques which rely upon representative examples

perform markedly less well in the context of Pro-Con phrases. Our constrained optimization
 31

approach dispenses with the need for representative examples and knowledge of grammatical

rules (Lee 2005). An entirely different approach that would preserve the unsupervised nature of

our work is to attempt to identify phrases through frequent item-set analysis. Hu and Liu (2004)

demonstrate that by tuning support and confidence thresholds, it is possible to discover whether a

word pair represents one concept or two (e.g. “compact flash” versus “3x zoom”).

Our assignment strategy uses word graphs based on co-occurrences. Although our use of

optimization to cluster words within a graph is unique, the graph representation is not new. Co-

clustering (Baker and McCallum 1998; Dhillon, Mallela et al. 2002) and categorical clustering

strategies (Gibson, Kleinberg et al. 1998; Ganti, Gehrke et al. 1999; Zaki and Peters 2005) model

the problem similarly.

Pragmatic considerations

We need the ability to assess the stability of our clusters and concomitant product

features. One instance of stability is sensitivity to data sample size. Here, we relied upon a large

data set to yield the phrases from which we identify a maximal clique and hence do assignment.

The large data set is also a boon because we can liberally discard phrases to minimize the effects

of naïve parsing. To measure the sensitivity to sample size, we would cross-validate on smaller

sets of review samples. We can plot the trade-off between sample size and evaluation metrics to

identify diminishing returns and attempt to estimate a minimal number of required reviews. Care

needs to be taken to ensure sufficient heterogeneity in the sample selection with respect to

different product features and the corresponding feature attributes.

While our approach is generalizable across different product domains, our dependence on

sources that provide phrase-like strings is a limitation. At least two factors ameliorate this
 32

limitation. First, there are other domains where phrase-like text-strings apply as opposed to

prose. Progress notes in medical records and online movie reviews (Eliashberg and Shugan

1997) are two such examples. Second, recognizing the current limitations of natural language

processing tools, more online sources are soliciting customer feedback in the form of phrases

rather than prose to facilitate automated processing (Google 2007).

Finally, the distinction between attributes, dimensions, and levels is imprecise.

Conceptually, each attribute is parameterized by one or more dimensions and each dimension is

defined by the levels (the set of values) that a particular dimension may take. Operationally,

attributes, dimensions, and levels are defined by the clustering. Attributes name the clusters

from K-means. The sub-clusters formed from the clique-based assignment each represent an

attribute’s dimension. The values within each sub-cluster define the dimension’s levels.

Knowing that the distinction between attributes, dimensions, and levels is noisy emphasizes the

role of text-processing as a decision-aid to marketing managers rather than as a substitute for

traditional processes.

Future work

In addition to work expanding the conceptual and pragmatic dimensions of our work,

there are a number of ways in which we might enrich the concept relationships that we are

learning. For example, some attribute properties are ordinal in nature. Recognizing order

facilitates the challenge of aligning orderings. For marketing and product design, alignment is

critical because different customers may address a concept using parallel categories. For

example, will 32 mb satisfy a customer seeking to store 130 images? We can apply concept

clustering (Gibson, Kleinberg et al. 1998; Ganti, Gehrke et al. 1999) in conjunction with our

CLP approach to group words from parallel categories.

 33

Structure exists not only at the market level but also at the level of individual consumers

(Elrod, Russell et al. 2002). A deeper understanding of the distinctions between segments

requires understanding not only the differences between product attributes but also the

differences in the underlying customer needs (Srivastava, Alpert et al. 1984; Allenby, Fennell et

al. 2002; Yang, Allenby et al. 2002). Unlike traditional data sources for market structure

analysis, online product reviews include comments about not only what and how, but why. In the

text of reviews, customers often relate why they purchased a product and what they use that

product for. Recent research mining user needs from online reviews (Lee 2004; Lee 2009) could

be incorporated into market structure analysis.

Finally, we provide an approach for descriptive modeling of market structure analysis

based upon online product reviews. However, traditional approaches to market structure analysis

produce models useful not only for describing existing markets but also for predictive purposes.

Exploring the integration of the Voice of the Consumer and productive reviews into a predictive

market structure analysis is a great opportunity (Allenby, Fennell et al. 2002; Elrod, Russell et al.

2002).

Learning from reviews offers a principled approach to selecting key attributes for

studying the structure of the existing market as well as defining studies to enable product

repositioning and/or new product design within that market. Moreover, our approach

emphasizes not only what but how. Identifying distinct voices with which customers describe a

product and changes in those voices over time, may reveal subtle differences in sub-markets and

represent a significant opportunity for better managing the consumer – producer relationship.

We believe that our research can be an important first step in that direction.
 34

REFERENCES

Allenby, G., G. Fennell, et al. (2002). "Market Segmentation Research: Beyond Within and

Across Group Differences." Marketing Letters 13(3): 11.

Archak, N., A. Ghose, et al. (2007). Show me the money! Deriving the Pricing Power of Product

Features by Mining Consumer Reviews. ACM KDD. San Jose, CA.

Baker, D. and A. McCallum (1998). Distributional Clustering of Words for Text Classification.

SIGIR 98.

Chen, Y. and J. Xie (2004). Online Consumer Review: A New Element of Marketing

Communications Mix. SSRN, http://ssrn.com/abstract=618782

DeSarbo, W. S., D. J. Howard, et al. (1991). "Multiclus: A new method for simultaneously

performing multidimensional scaling and cluster analysis." Psychometrika 56(1): 16.

Dhillon, I. S., S. Mallela, et al. (2002). Enhanced Word Clustering for Hierarchical Text

Classification. ACM SIGKDD.

Eliashberg, J. and S. Shugan (1997). "Film Critics: Influencers or Predictors?" Journal of

Marketing 61: 68-78.

Elrod, T. (1988). "Choice Map: Inferring a Product-Market Map from Panel Data." Marketing

Science 7(1): 19.

Elrod, T. (1991). "Internal Analysis of Market Structure: Recent Developments and Future

Prospects." Marketing Letters 2(3): 14.

Elrod, T., G. J. Russell, et al. (2002). "Inferring Market Structure from Customer Response to

Competing and Complementary Products." Marketing Letters 13(3): 12.

Erdem, T. and M. P. Keane (1996). "Decision-Making Under Uncertainty: Capturing Dynamic

Choice Processes in Turbulent Consumer Good Markets." Marketing Science 15(1): 20.
 35

Everitt, B. S. and G. Dunn (2001). Applied Multivariate Data Analysis. New York, Oxford

University Press.

Evgeniou, T., C. Boussios, et al. (2005). "Generalized Robust Conjoint Estimation." Marketing

Science 24(3): 415-429.

Feldman, R., M. Fresko, et al. (2007). Extracting Product Comparisons from Discussion Boards.

IEEE ICDM.

Feldman, R., M. Fresko, et al. (2008). Using Text Mining to Analyze User Forums. International

Conference on Service Systems and Service Management.

Ganti, V., J. Gehrke, et al. (1999). CACTUS - Clustering categorial data using summaries. ACM

SIGKDD, San Diego, CA.

Ghose, A. and P. Ipeirotis (2008). Estimating the Socio-Economic Impact of Product Reviews:

Mining Text and Reviewer Characteristics. New York, New York University.

Ghose, A., P. Ipeirotis, et al. (2009). Towards Designing Ranking Systems for Hotels on Travel

Search Engines Combining Text Mining an Image Classification with Econometrics.

WITS. Phoenix, AZ.

Ghose, A., P. Ipeirotis, et al. (2006). The Dimensions of Reputation in Electronic Markets, New

York University: 32.

Gibson, D., J. Kleinberg, et al. (1998). Clustering categorical data: an approach based on

dynamical systems. 24th International Conference on Very Large Databases (VLDB).

Goldberg, S. M., P. E. Green, et al. (1984). "Conjoint Analysis of Price Preimums for Hotel

Amenities." Journal of Business 57(1): 111-132.

Google (2007). About Google Base, Google

 36

Green, P. E. and A. M. Krieger (1991). "Segmenting Markets with Conjoint Analysis." Journal

of Marketing 55: 20-31.

Green, P. E. and V. Srinivasan (1978). "Conjoint Analysis in Cosumer Research: Issues and

Outlook." Journal of Consumer Research 5: 103-123.

Greenacre, M. J. (1992). "Correspondence Analysis in Medical Research." Statistical Methods in

Medical Research 1: 97-117.

Griffin, A. and J. R. Hauser (1993). "The Voice of the Customer." Marketing Science 12(1): 1-

27.

Hearst, M. (1992). Automatic acquisition of hyponyms from large text corpora. COLING.

Nantes, France: 539-545.

Hill, S., F. Provost, et al. (2006). "Network-based Marketing: Identifying likely adopters via

consumer networks." Statistical Science 21: 21.

Hillier, F. S. and G. J. Lieberman (2001). Introduction to Operations Research, McGraw-Hill.

Hu, M. and B. Liu (2004). Mining and Summarizing Customer Reviews. KDD04. Seattle, WA.

Huber, J. and K. Zwerina (1996). "The Importance of Utility Balance in Efficient Choice

Designs." Journal of Marketing Research 33: 307-317.

Kamakura, W. A. and G. J. Russell (1989). "A Probabilistic Choice Model for Market

Segmentation and Elasticity Structure." Journal of Marketing Research 26(4): 12.

Kilgarriff, A. (2001). "Comparing Corpora." International Journal of Corpus Linguistics 6(1):

97-133.

Krzanowski, W. J. and Y. T. Lai (1988). "A criterion for determing the number of groups in a

data set using sum-of-squares clustering." Biometrics 44: 12.

Lee, T. (2004). Use-centric mining of customer reviews. WITS. Washington, D.C.: 146-151.
 37

Lee, T. (2005). Ontology Induction for Mining Experiential Knowledge from Customer

Reviews. Utah WISC. Salt Lake City, UT.

Lee, T. Y. (2009). Automatically Learning User Needs from Online Reviews for New Product

Design. AMCIS. San Francisco, CA.

Lehmann, D. R., S. Gupta, et al. (1997). Marketing Research, Prentice Hall.

Liu, B., M. Hu, et al. (2005). Opinion Observer: Analyzing and Comparing Opinions on the

Web. WWW. Chiba, Japan, ACM.

Maedche, A. and S. Staab (2000). Semi-automatic Engineering of Ontologies from Text. SEKE.

Michalek, J. J., F. M. Feinberg, et al. (2005). "Linking Marketing and Engineering Product

Design Decisions via Analytical Target Cascading." J of Product Innovation Management

22: 42-62.

Moore, W. L., J. Gray-Lee, et al. (1998). "A Cross-Validity Comparison of Conjont Analysis and

Choice Models at Different Levels of Aggregation." Marketing Letters 9(2): 195-207.

Moore, W. L., J. J. Louviere, et al. (1999). "Using Conjoint Analysis to Help Design Product

Platforms." Journal of Product Innovation Management 16: 27-39.

Nasukawa, T. and J. Yi (2003). Sentiment Analysis: Capturing Favorability Using Natural

Language Processing. K-CAP. Sanibel Island, Florida, ACM: 70-7.

Pang, B. and L. Lee (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in

Information Retrieval.

Pant, G. and O. Sheng (2009). Avoiding the Blind Spots: Competitor Identification Using Web

Text and Linkage Structure. ICIS. Phoenix, AZ.

Pereira, F., N. Tishby, et al. (1993). Distributional Clustering of English Words. ACL93.
 38

Popescu, A.-M. and O. Etzioni (2005). Extracting Product Features and Opinions from Reviews.

HLT-EMNLP.

Popescu, A.-M., A. Yates, et al. (2004). Class extraction from the World Wide Web. AAAI

Workshop on ATEM.

Randall, T., C. Terwiesch, et al. (2007). "User Design of Customized Products." Marketing

Science 26(2): 268-280.

Salton, G. and M. McGill (1983). Introduction to modern information retrieval. New York,

McGraw-Hill.

Srivastava, R. K., M. I. Alpert, et al. (1984). "A Customer-Oriented Approach for Determining

Market Structures." Journal of Marketing 48(2): 14.

Tibshirani, R., G. Walther, et al. (2005). "Cluster validation by prediction strength." Journal of

Computational & Graphical Statistics 14(3): 18.

Toubia, O., D. I. Simester, et al. (2003). "Fast Polyhederal Adaptive Conjoint Estimation."

Marketing Science 22(3): 273-303.

Turney, P. (2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to

Unsupervised Classification of Reviews. ACL: 417-424.

Ulrich, K. and S. Eppinger (2003). Product Design and Development, McGraw-Hill.

Urban, G. L. and J. R. Hauser (1993). Design and Marketing of New Products, Prentice Hall.

Urban, G. L., P. L. Johnson, et al. (1984). "Competitive Market Structure." Marketing Science

3(2): 30.

West, P. M., C. L. Brown, et al. (1996). "Consumption Vocabulary and Preference Formation."

Journal of Consumer Research 23(2): 16.

 39

Wittink, D. R. and P. Cattin (1989). "Commercial Use of Conjoint Analysis: An Update."

Journal of Marketing 53: 91-96.

Wittink, D. R., L. Krishnamurthi, et al. (1982). "Comparing derived importance weights across

attributes." Journal of Consumer Research 10(1): 471-74.

Yang, S., G. Allenby, et al. (2002). "Modeling Variation in Brand Preference: The Roles of

Objective Environment and Motivating Conditions." Marketing Science 21: 18.

Zaki, M. and M. Peters (2005). CLICKS: Mining Subspace Clusters in Categorical Data via K-

partite Maximal Cliques. ICDE05.

Zhao, Y. and G. Karypis (2002). Criterion Functions for Document Clustering: Experiments and

Analysis. University of Minnesota Deptartment of Computer Science/Army HPC

Research Center. Minneapolis, MN, University of Minnesota: 30.

 40

TABLES

Maximal clique nice 6x optic zoom

Original phrase Phrases as constraints D1 D2 D3 D4
Zoom zoom zoom
Long 6x optical zoom long 6x optic zoom long 6x optic zoom
standard 3x optical zoom standard 3x optic zoom standard 3x optic zoom
nice optical zoom nice optic zoom nice optic zoom
6x zoom is nice 6x zoom nice nice 6x zoom
5x optical zoom 5x optic zoom optic zoom
Table 1: Attributes and their dimensions as an assignment problem

Optical Floppy Support

LCD Memory/Screen Shutter (delay, lag) Shoot
(zoom, viewfinder) (storage media) (service)
Lens Print Slow (start-up, Flash (memory Body (design,
Red Eye USB
(cap, quality, mfr) (size, quality, output) turn on, recovery) card, photo) construction)
Picture Cover Feel Battery Movie
Price Size
(what, where) (lens, LCD, battery) (mfr, construction) (life, use, type) (audio, visual)
Focus Edit (in camera) Disk Instruction Photo quality Menu Control
Features Adapter (AC) MB (memory) Low light Picture quality Resolution Zoom
Software Image (quality) Macro (lens) Megapixel
Table 2: Automatically generated product attributes

Total # Evaluating product attributes

Total #
Reference attributes +
attributes P R P+ R+
dimensions
Epinions (A) 5 29 0.10 0.60 0.13 0.80
DPReview 26 90 0.23 0.19 0.49 0.54
Megapixel 6 37 0.10 0.50 0.18 0.83
Bizrate 15 85 0.31 0.47 0.41 0.73
CNet 17 62 0.33 0.53 0.46 0.76
Epinions (B) 14 21 0.36 0.64 0.51 1.00
CR02 20 N/A 0.23 0.40 0.36 0.65
CR03 20 N/A 0.26 0.40 0.33 0.55
CR04 20 N/A 0.36 0.50 0.49 0.75
CR05 20 N/A 0.28 0.45 0.33 0.55
Table 3: Evaluating attributes and levels, k = 50

Auto E(A) DP Mega Biz Cnet E(B) CR02 CR03 CR04 CR05 Mean

Precision 0.37 0.69 0.33 0.57 0.41 0.27 0.48 0.24 0.26 0.27 0.37 0.42

Recall 0.72 0.23 0.55 0.23 0.48 0.33 0.46 0.38 0.37 0.37 0.50 0.39
Table 4: Internal consistency: average precision and recall between one source and all others
 41

Before 2005 Size Support (service) Feel (mfr) Instruction Edit (in camera)
After 2005 ISO Modes Accessories Easy to use White/color balance
Table 5. Changes in automatically generated attributes between 2004 and 2005-2008

Manufacturer Rack (broiler, toast) Crumb tray; Easy to clean

Heat (reliably; quickly) Price (pricey, expensive) Beeper/bell
Look; appearance Toast Easy to clean
Warranty (reliability) Design/Style Controls; Space (counter)
Bake (evenly) Cook (quickly); Footprint Brown (cooking)
Timer Exterior (hot surface) Appliance/finish
Table 6. Automatically generated product attributes for Toaster Ovens

Room (size, appearance) Bar Park (valet, fee, price, charge) Staff (front desk; friendly) Business Center Problem
Hotel (size, cleanliness) Car Surround (neighborhood) Internet wireless Feel Location
Shuttle (service) Pool Noise (street, highway, construction) Close (location, sights) Furnishings View
Concierg (Amenities) Cost Facil (conference, laundry, exercise) Downtown (park, location) Stay Lack
Air condit (noise) TV Water (bottle, shower, pressure) Staff (atmosphere) Public area
Place (look, modern) Bed Food, accommodations, pillow Property (architecture) Citi (location)
Table 7. Automatically generated product attributes from TripAdvisor
 42

FIGURES

Figure 1: Heuristic Description of Text Processing of User-Generated Pro-Con lists

 43

Figure 2. User assessments of familiarity vs. importance

 44

Figure 3. Mapping the market using customer reviews

 45

Figure 4. Customer mapping of the brands using user-generated polarity

 46

Figure 5. Positive polarity and changes in market structure over time

 47

Figure 6. Mapping digital cameras; positive polarity over time

 48

Figure 7. Mapping the market structure of toaster ovens

 49

Figure 8. Mapping the positive polarity of hotel reviews

 50

Figure 9. Mapping the negative polarity of hotel reviews

 51

Appendix 1. Algorithmic Details

In this Appendix, we elaborate on specific details of the text-processing algorithms.

[1] Vector space model and word importance

Borrowing from the information retrieval community, our phrase  word matrix is a

representation of the vector-space model (VSM). More formally, j  J is a word in the set of all words; i

 I is a phrase. A phrase is simply a finite sequence of words and J is a subset of the set of finite word

sequences I = {<j>| j  J}. We define an initial phrase  word matrix as a simple variation on the term-

frequency inverse-document-frequency (TF-IDF) VSM (Salton and McGill 1983):

Matrix(i,j) = (TFij  IPFj) (A1.1)

 
where the term frequency TFij counts the total number of occurrences of word j in the instances of

phrase i. The inverse phrase frequency IPFj = log(|I|/nj) is a weighting factor for words that are more

helpful in distinguishing between different product attributes because they only appear in a fraction of the

total number of unique phrases. If |I| represents the total number of unique phrases in the review

collection, nj counts the total number of unique phrases containing word j.

A limitation of the TF-IPF weighting is that there are still some terms (e.g. sentiment words like

"great" or "good") that are neither stop words nor product attributes yet appear with product attributes in

the TF-IDF matrix. As an additional discount factor beyond IPF, we automatically gather words from a

second set of K phrases using online reviews for an unrelated product domain. Intuitively, words

appearing in the reviews for unrelated products are less likely to represent relevant product attributes for

the focal one. For example, words describing digital camera attributes are less likely to also appear in

vacuum cleaner reviews.

Formally, for a set of (I') phrases drawn from the set of finite word sequences over j  J, we

calculate rank(j) = rank(TF'ijIPF'j) where higher weighted frequencies correspond to higher rank. Note
 52

that multiple words may share the same rank; if we define words that do not appear in any phrase as

having IPF'j = 0, then we may say:


Matrix(i,j) = TFij  rank  j   IPF j  IPF ' j  (A1.2)

Thus, we scale TF by the rank of the word in the unrelated product domain and scale the IPF by IPF'

from the unrelated product domain.

[2] Graph representations

To discover attributes, we assume that each customer review phrase corresponds to a distinct

product attribute. To discover attribute dimensions, we assume that each word in the phrase corresponds

to a distinct dimension. Discovering attribute dimensions then reduces to the assignment of particular

words to attribute dimensions. But how do we know how many dimensions there are in the assignment

problem? Is it possible that the assignment optimization has no feasible solution because of conflicting

constraints due to noise from the vagaries of human language? To solve this problem, we generate a

graph of all words in the cluster. Each word is a node and arcs are defined by the co-occurrence of two

words in the same phrase. We partition the graph into (possibly overlapping) sub-graphs by searching for

maximal cliques. Intuitively, each sub-graph represents a maximal subset of words and phrases for which

an optimal solution exists. The size of the maximal clique sets the number of attributes |D|. The sub-

graph (words J and phrases I) define the optimization.

More formally, we assume that phrases and words are preprocessed and normalized into words as

before. A graph G = (V,E) is a pair of the set of vertices V and the set of edges E. An edge in E is a

connection between two vertices and may be represented as a pair (vi,vj)  V. Each phrase (word)

represents a vertex v in the graph; edges are defined by phrase pairs within a review (word pairs within a

phrase). An N-partite graph is a connected graph where there are no edges in any set of vertices Vi. A

clique of size N simulates a plays the role of arelational schema and can be extended to an N-partite

graph by substituting each vertice vi of the clique with a set of vertices Vi. A database table with disjoint
 53

columns thus represents an N-partite graph where the size of the clique defines the number of columns

and each word in the clique “names” a column. A maximal-complete-N-partite graph is a complete-N-

partite graph not contained in any other such graph; in other words, the initial clique is maximal. The

corresponding database table of phrases represents the existing product attribute space, and the maximal-

complete-N-partite graph includes possibly novel combinations of previously unpaired attributes and/or

attribute properties.

To relate the graph back to customer reviews, we say that a product attribute is constructed from k

dimensions. Each dimension names a domain (D). Each domain D is defined by a finite set of words that

includes the value NULL for review phrases where customers fail to mention one or more attribute

dimension(s). The Cartesian product of domains D1 …Dk is the set of all k-tuples {t1…tk | ti  Di}. Each

phrase is simply one such k-tuple and the set of all phrases in the cluster simply defines a finite subset of

the Cartesian product. A relational schema is simply a mapping of attribute properties A1 …Ak to domains

D1 … Dk. Note the strong, implicit assumption that a maximal clique, taken over a word graph, is a proxy

for the proper number of attribute dimensions. Under this assumption, it is easy to see how searching for

cliques within the graph results in a table.

[3] Constrained Logic Programming

To align words into their corresponding attribute dimensions, we frame the task as a

mathematical assignment problem and resolve the problem using a bounds consistency approach. We

process_phrases(p_list)
[1] schema = find_maximal_clique(p_list)
[2] order phrases by length
[3] for each phrase p:
[4] # initialize data structures
[5] tok_exclusion – for each tok, mutually exclusive tokens
[6] tok_candidates – for each tok, valid candidate assignments
[7] tok_assign – for each tok, the dimension assignment
[8] # propagate the constraints for each successive phrase
[9] tok_candidates, tok_exclusion, tok_assign =
[10] propagate_bounds(phrase, tok_candidates,
[11] tok_exclusion, tok_assign, schema)
Figure 2. Logical Assignment
 54

define the assignment using the maximal clique that corresponds to the schema for each product attribute

table (see Figure 2). In the bounds consistency approach, we invert the constraints (tok_exclusion) to

express the complementary set of candidate assignments (tok_candidates) for each attribute dimension. If

the phrase constraints, taken together, are internally consistent, then the candidate assignments

(tok_assign)for a given token are simply the intersection of all candidate assignments as defined by all

phrases in the cluster containing that token.

We transform the mutual exclusivity constraint represented by each phrase into a set of candidate

assignments using the algorithm in Figure 3. Note that we need only propagate the mutual exclusivity of

words that are previously unassigned. Accordingly, for each unassigned token in a given phrase, the set

of candidate assignments is the intersection of the possible assignments based upon the current phrase and

all candidate assignments from earlier phrases containing the same token. We maintain a list of active

tokens boundary_list to avoid rescanning the set of all tokens every time the possible assignments for a

given token is updated.

propagate_bounds(phrase, tok_candidates, tok_exclusion, tok_assign, schema)

[1] # marshall prior assignments

[2] unassigned_tok = {t|tphrase  tassign_d}
[3] unassigned_attr = {a|aschema  t(tphrase  atok_assign[t])}
[4] for each t in unassigned_tok:
[5] tok_exclusion[t] = (t  (unassigned_tok – t))⋃ tok_exclusion[t]
[6] possible_assign = {a|a(unassigned_attr ⋂ tok_candidates[t])}
[7] boundary_list = {(t,[possible_assign])} ⋃ boundary_list
[8] recurse_boundary(boundary_list, tok_exclusion, tok_assign)
Figure 3. Propagate boundary constraints

Finally, the K-means clustering used to separate review phrases into distinct product attributes is

a noisy process. The clustering can easily result in the inclusion of spurious phrases. Both the initial

clustering of phrases into product attributes and the subsequent assignment of words to attribute

properties are inherently imperfect. Inconsistencies may emerge for any number of reasons including:

Poor parsing, the legitimate appearance of one word multiple times within a single phrase (e.g. the phrase

‘digital zoom and optical zoom’ duplicates the word ‘zoom’) or even “inaccuracies” by the human
 55

reviewers who write the text that is being automatically processed. This could result in a single attribute

property divided over multiple table columns. For example, some reviews might write "SmartMedia" as a

single word and others might use "Smart" and "media" as two separate words. Alternatively, multiple

product attributes may appear in the same cluster. '[C]ompact flash' and 'compact camera' are clustered

together based upon their common use of the word 'compact,' yet refer to distinct attributes.

To address the problem of robustness in the face of noisy clusters that include references to additional

product attributes or have different properties for the same attributes, we extend our CLP approach to

simultaneously cluster phrases and assign words. By modeling reviews as a graph of phrases, we can

apply the same CLP in a pre-assignment step to filter a single (noisy) cluster of phrases. As alluded to in

Appendix 2.2, we generate a graph where phrases are nodes, and edges represent the co-occurrence of

two phrases within the same review. The extended CLP then prunes phrases by recursively applying co-

occurrence constraints; two phrases in the same review cannot describe the same attribute just as two

words in the same phrase cannot describe the same attribute dimension. The same assignment

representation removes phrases that are not central to the product attribute at the heart of a particular

phrase cluster. Phrases that are not “connected” in the graphical sense of a connected component or

represent conflicting constraints are simply excluded from the subcluster.

Unfortunately, even the extended CLP approach is imperfect. Some of the tables will represent

distinct product attributes. Others will simply constitute random noise. Individual tables are supposed to

represent distinct product attributes, so we assume that meaningful tables should contain minimal word

overlap. With this in mind, we apply a two-stage statistical filter to further filter noisy clusters.

First, because each table itself separates tokens into attribute properties (columns), meaningful

tables will not hold too small a percentage of the overall number of tokens. Second, we assume that

meaningful tables comprise a (predominately) disjoint token subset. If the tokens in a table appear in no

other table, then the intra-table token frequency should match the frequency of the initial k-means cluster;

likewise, the table's tokens, when ordered by frequency, should match the relative frequency-based order
 56

of the same tokens within the initial cluster. The first stage of our statistical filter is evaluation of a 2

statistic, comparing each table to its corresponding initial cluster. Although there is no hypothesis to be

tested per se, there is a history of applying the 2 statistic in linguistics research to compare different sets

of text with a measure that weights higher-frequency tokens with greater significance than lower

frequency tokens (Kilgarriff 2001). In our case, we set a minimum threshold on the 2 statistic to ensure

that individual tables reflect an appropriate percentage of tokens from the initial cluster.

After filtering out tables that do not satisfy the 2 threshold, we use the same cluster token counts

to calculate rank order statistics. We compare the token rank order from each constituent table to that in

the corresponding initial cluster using a modified Spearman rank correlation co-efficient (rs). As a minor

extension, we use the relative token rank, meaning that we maintain order but keep only tokens that are in

both the initial and the iterated CLP cluster(s). We select as significant those tables that maximize rs. In

the event that two or more tables maximize rs we promote all such subclusters either as a noisy cluster or

as synonymous words for the same product attribute as determined by a manual reading.
 57

Appendix 2. User survey

In this Appendix, we list the digital camera product attributes (with duplicates eliminated) that are

found exclusively in one or more online buying guides (Expert Only), learned automatically from the

product reviews (VOC Only), or in both (Expert + VOC). The means for Familiarity and Importance as

collected from our survey are reported on a 1 to 7 scale. To help align the attribute names used here with

those in Table 2, we include a mapping from the automatically derived attribute clusters (auto) to those 55

attributes used in the consumer survey. Note that in some cases, an automatically derived attribute is

mapped to more than one survey (expert) attribute name and vice versa due to inconsistencies between the

granularity with which an attribute is discussed in the expert guides and/or by the voice of the consumer.

Expert Only
Familiarity Importance
battery source 6.42 6.05
flash ext 4.91 3.09
flash range 4.17 3.90
image compress 4.80 4.62
image sensor 2.37 3.25
image stab 4.88 5.28
man light sens 3.69 3.69
manual exp 2.69 3.10
manual light meter 2.38 2.86
manual shut 3.09 3.24
mem qty built-in 5.68 5.05
movie fps 4.43 4.35
movie output 3.90 4.20
music play 4.57 3.80
num sensors 2.25 3.18
power adapt 6.05 4.87
time lapse 4.45 3.76
wide angle 3.57 3.57
 58

VOC Only
Survey attribute Auto Familiarity Importance
camera size size 6.35 5.87
body (design) body 5.82 5.48
download time USB 5.68 4.75
feel (durability) feel; support service 5.30 5.43
instructions instruction 6.07 4.18
lcd brightness screen 4.62 4.57
shutter lag slow; shutter 3.87 3.80
twist lcd cover 3.80 3.62

Expert + VOC
Auto Familiarity Importance
battery life battery 6.50 6.30
cam soft edit 5.32 3.57
cam type shoot 4.65 5.06
comp cxn USB 6.13 5.75
comp soft software 5.77 4.60
ergonomic feel feel 5.15 4.83
flash built-in red-eye 6.45 6.26
flash mode low-light; red-eye 5.48 5.12
lcd viewfinder lcd 5.00 5.15
lens cap cover; lens 4.92 4.25
lens type macro 3.80 4.20
manual aper control 2.40 2.86
manual focus control; focus 5.14 3.72
mem capacity mb 5.30 5.68
mem stor type disk; floppy; flash (drive) 5.63 5.47
movie audio movie 4.85 4.48
movie length movie 5.73 5.47
movie res mpeg 4.97 5.15
navigation menu 5.93 5.40
optical viewfinder optical 4.50 4.33
photo qual; picture; print;
picture quality image qual 6.35 6.60
price price 6.31 6.45
resolution resolution; megapixel 5.35 5.56
 59

shot modes features 5.55 4.67

shutter delay slow; shutter 4.27 3.95
shutter speed control 4.81 4.60
white bal features 3.40 3.74
zoom dig zoom 5.07 4.47
zoom opt zoom; optical 5.52 5.21
 60

Appendix 3. Interpreting the Correspondence Analysis dimensions.

Correspondence Analysis is an approach to dimension reduction when analyzing high-dimensional, two-

mode, two-way count data (Everitt and Dunn 2001). To interpret the dimensions in the reduced space, we

regressed each brand’s factor scores on the derived attributes. For each figure in the paper, we report the

results of the stepwise regression on F1 and F2. The reported results assume a probability for entry of

0.05 and a probability of removal of 0.1.

Figure 3. Mapping the market using customer reviews

Summary of attribute selection for dimension F1 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr  23  IN  0.012  0.975 0.974
2  Attr  20  IN  0.002  0.996 0.995
3  Attr  31  IN  0.001  0.998 0.998
4  Attr  17  IN  0.000  0.999 0.999
5  Attr  42  IN  0.000  0.999 0.999
6  Attr  21  IN  0.000  1.000 1.000

Summary of attribute selection for dimension F2 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr  6  IN  0.059  0.800 0.792
2  Attr  26  IN  0.033  0.893 0.885
3  Attr  20  IN  0.020  0.938 0.931
4  Attr  31  IN  0.009  0.972 0.968
5  Attr  3  IN  0.005  0.984 0.981
6  Attr  48  IN  0.004  0.990 0.987
7  Attr 38  IN  0.003  0.993 0.990

Figure 4. Customer mapping of the brands using user-generated polarity

Same dimensions as those in Figure 3.

 61

Figure 5. Positive polarity and changes in market structure over time

Summary of attribute selection for dimension F1 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 20  IN  0.019  0.887 0.880
2  Attr 32  IN  0.010  0.946 0.939
3  Attr 8  IN  0.007  0.965 0.957
4  Attr 11  IN  0.004  0.980 0.974
5  Attr 40  IN  0.003  0.989 0.984
6  Attr 1  IN  0.001  0.996 0.994

Summary of attribute selection for dimension F2 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 3  IN  0.028  0.591 0.565
2  Attr 37  IN  0.014  0.812 0.787
3  Attr 50  IN  0.007  0.916 0.898
4  Attr 15  IN  0.004  0.949 0.933
5  Attr 25  IN  0.002  0.975 0.965
6  Attr 14  IN  0.001  0.988 0.981
7  Attr 41  IN  0.001  0.994 0.991

Figure 6. Mapping digital cameras; positive polarity over time

Summary of attribute selection for dimension F1 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 50  IN  0.006  0.906 0.901
2  Attr 3  IN  0.004  0.951 0.944
3  Attr 11  IN  0.002  0.973 0.967
4  Attr 31  IN  0.001  0.984 0.979
5  Attr 22  IN  0.001  0.990 0.985
6  Attr 17  IN  0.000  0.995 0.992
 62

Summary of attribute selection for dimension F2 from 39 attribute clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 49  IN  0.015  0.649 0.627
2  Attr 41  IN  0.007  0.845 0.824
3  Attr 32  IN  0.001  0.970 0.964
4  Attr 48  IN  0.001  0.982 0.976
5  Attr 40  IN  0.001  0.988 0.983
6  Attr 3  IN  0.000  0.995 0.993

Figure 7. Mapping the market structure of toaster ovens

Summary of attribute selection for dimension F1 from 18 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 4  IN  0.003  0.769 0.750
2  Attr 16  IN  0.001  0.907 0.890

Summary of attribute selection for dimension F2 from 18 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 23  IN  0.006  0.581 0.546
2  Attr 11  IN  0.003  0.815 0.781
3  Attr 8  IN  0.001  0.939 0.921

Figure 8. Mapping the positive polarity of hotel reviews

Summary of attribute selection for dimension F1 from 34 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 22  IN  0.027  0.751 0.726
2  Attr 18  IN  0.007  0.944 0.932
3  Attr 10  IN  0.004  0.969 0.957
4  Attr 12  IN  0.002  0.984 0.002
5  Attr 16  IN  0.001  0.994 0.001
6  Attr 15  IN  0.001  0.998 0.001
7  Attr 2  IN  0.000  0.999 0.000
 63

Summary of attribute selection for dimension F2 from 34 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 20  IN  0.040  0.539 0.493
2  Attr 9  IN  0.022  0.774 0.724
3  Attr 7  IN  0.007  0.938 0.915
2  Attr 20  OUT  0.006  0.936 0.922
3  Attr 5  IN  0.003  0.973 0.964
4  Attr 24  IN  0.001  0.994 0.990
5  Attr 8  IN  0.000  0.997 0.995

Figure 9. Mapping the negative polarity of hotel reviews

Summary of attribute selection for dimension F1 from 34 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 10  IN  0.022  0.890 0.879
2  Attr 6  IN  0.007  0.970 0.963
3  Attr 12  IN  0.004  0.985 0.980
4  Attr 9  IN  0.001  0.997 0.995

Summary of attribute selection for dimension F2 from 34 attributes clusters.

No. of Attribute Status MSE R2 Adjusted

Attributes R2
1  Attr 11  IN  0.050  0.595 0.554
2  Attr 10  IN  0.011  0.920 0.902
3  Attr 25  IN  0.004  0.973 0.962
4  Attr 19  IN  0.002  0.988 0.982
5  Attr 13  IN  0.001  0.997 0.994

ENDNOTES

1
Interested readers may contact the corresponding author for the source code for all of the

algorithms described within this research.

 64

2
Each subject also completed a six-item digital camera quiz after providing their self-

assessment. The correlation was high (r = 0.4) and hence we use the self-assessment score in

subsequent analysis.