The Role of Emotions for the Perceived Usefulness in Online Customer Reviews

Online customer reviews often express emotions. This can enable marketers to analyze the textual content of online reviews with the aim to understand the role of emotions and how they can affect other customers. In this paper, we present an approach to extracting emotion content from online reviews in order to measure the importance of various emotion dimensions within different product categories. The approach uses an emotion lexicon to extract emotion terms, while it also builds a classification model to measure the importance of emotion dimensions based on the quality of reviews. Review quality is measured based on the usefulness of online customer reviews, which are perceived and evaluated by other customers through their helpfulness ratings. This approach allows the identification of emotion dimensions that characterize qualitative reviews. The empirical evaluation in our study suggests that trust, joy, and anticipation are the most decisive emotion dimensions, although substantial variance across product categories can also be detected. Additionally, we compared two contrasting emotion dictionaries. One lexicon was crowd-funded and contained a large vocabulary, whereas the other was more focused and smaller, since it was created word-wise by an expert. Our empirical findings indicate that the crowd-funded solution outperforms its smaller counterpart in terms of classification precision. The main implication of this study is that it adds an emotional perspective to the broad set of existing tools that marketers employ to analyzing online reviews. Our contributions are: i) we are the first to analyze emotions' role in online customer reviews; ii) we demonstrate how to develop a big data model such as this, without external assistance; iii) we show how to interpret the results of the created model; and iv) we show which dictionary to prefer when creating the model.

[1]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[2]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[3]  Chris Callison-Burch,et al.  Creating Speech and Language Data With Amazon’s Mechanical Turk , 2010, Mturk@HLT-NAACL.

[4]  Yubo Chen,et al.  The Role of Marketing in Social Media: How Online Consumer Reviews Evolve , 2011 .

[5]  Jonah Berger,et al.  Positive Effects of Negative Publicity: When Negative Reviews Increase Sales , 2009, Mark. Sci..

[6]  Carlo Strapparava,et al.  WordNet Affect: an Affective Extension of WordNet , 2004, LREC.

[7]  Paul A. Pavlou,et al.  Evidence of the Effect of Trust Building Technology in Electronic Markets: Price Premiums and Buyer Behavior , 2002, MIS Q..

[8]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[9]  R. Plutchik.  On emotion: The chicken-and-egg problem revisited , 1985 .

[10]  X. Zhang,et al.  Impact of Online Consumer Reviews on Sales: The Moderating Role of Product and Consumer Characteristics , 2010 .

[11]  Hisashi Kashima,et al.  Learning from Crowds and Experts , 2012, HCOMP@AAAI.

[12]  Peter C. Neijens,et al.  "Highly Recommended!" The Content Characteristics and Perceived Usefulness of Online Consumer Reviews , 2011, J. Comput. Mediat. Commun..

[13]  Shawndra Hill,et al.  Expert Stock Picker: The Wisdom of (Experts in) Crowds , 2011, Int. J. Electron. Commer..

[14]  David Schuff,et al.  What Makes a Helpful Review? A Study of Customer Reviews on Amazon.com , 2010 .

[15]  Prashanth U. Nyer,et al.  The role of emotions in marketing , 1999 .

[16]  J. Arndt.  Role of Product-Related Conversations in the Diffusion of a New Product , 1967 .

[17]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[18]  J. Russell.  Is there universal recognition of emotion from facial expression? A review of the cross-cultural studies. , 1994, Psychological bulletin.

[19]  Bing Liu,et al.  Opinion spam and analysis , 2008, WSDM '08.

[20]  Miriam Solomon,et al.  Groupthink versus The Wisdom of Crowds: The Social Epistemology of Deliberation and Dissent , 2006 .

[21]  Jure Leskovec,et al.  Hidden factors and hidden topics: understanding rating dimensions with review text , 2013, RecSys.

[22]  Anol Bhattacherjee,et al.  Influence Processes for Information Technology Acceptance: An Elaboration Likelihood Model , 2006, MIS Q..

[23]  Eduard Hovy,et al.  What are Sentiment, Affect, and Emotion? Applying the Methodology of Michael Zock to Sentiment Analysis , 2015 .

[24]  K. Scherer.  What are emotions? And how can they be measured? , 2005 .

[25]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[26]  Brian T. Ratchford.  Some Directions for Research in Interactive Marketing , 2015 .

[27]  Raymond A. Patterson,et al.  Wisdom of the Crowds: Decentralized Knowledge Construction in Wikipedia , 2006 .

[28]  Thorsten Joachims,et al.  Learning to classify text using support vector machines - methods, theory and algorithms , 2002, The Kluwer international series in engineering and computer science.

[29]  E. Anderson.  Customer Satisfaction and Word of Mouth , 1998 .

[30]  José van Dijck,et al.  Wisdom of the crowd or technicity of content? Wikipedia as a sociotechnical system , 2010, New Media Soc..

[31]  K. Scherer,et al.  The why, the what, and the how of the GRID instrument , 2013 .

[32]  R. Plutchik.  The emotions: Facts, theories and a new model. , 1964 .

[33]  Pearl Pu,et al.  Are influential writers more objective?: an analysis of emotionality in review comments , 2014, WWW.

[34]  P. Ekman.  An argument for basic emotions , 1992 .

[35]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[36]  Audun Jøsang,et al.  A survey of trust and reputation systems for online service provision , 2007, Decis. Support Syst..

[37]  Ephraim R. McLean,et al.  The DeLone and McLean Model of Information Systems Success: A Ten-Year Update , 2003, J. Manag. Inf. Syst..

[38]  Jaime G. Carbonell,et al.  Active Learning and Crowd-Sourcing for Machine Translation , 2010, LREC.

[39]  R. Plutchik.  A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMOTION , 1980 .

[40]  Thomas K. Srull,et al.  The Effects of Subjective Affective States on Memory and Judgment , 1984 .

[41]  Victoria D. Bush,et al.  What We Know and Don't Know about Online Word-of-Mouth: A Review and Synthesis of the Literature , 2014 .

[42]  Qing Cao,et al.  Exploring determinants of voting for the "helpfulness" of online user reviews: A text mining approach , 2011, Decis. Support Syst..

[43]  Fernando R. Jiménez,et al.  Too Popular to Ignore: The Influence of Online Reviews on Purchase Intentions of Search and Experience Products , 2013 .

[44]  Pearl Pu,et al.  Prediction of Helpful Reviews Using Emotions Extraction , 2014, AAAI.

[45]  M. Bradley,et al.  Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings , 1999 .

[46]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[47]  Hillary Anger Elfenbein,et al.  On the universality and cultural specificity of emotion recognition: a meta-analysis. , 2002, Psychological bulletin.

[48]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[49]  Matthew K. O. Lee,et al.  The impact of electronic word-of-mouth: The adoption of online opinions in online customer communities , 2008, Internet Res..

[50]  Frank Schweitzer,et al.  Emotions in Product Reviews--Empirics and Models , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[51]  Panagiotis G. Ipeirotis,et al.  Estimating the Helpfulness and Economic Impact of Product Reviews: Mining Text and Reviewer Characteristics , 2010, IEEE Transactions on Knowledge and Data Engineering.