Emotions in Online Reviews to Better Understand Customers’ Brand Perception

  • Armin FelbermayrEmail author
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 263)


Measuring customers’ opinions based on online customer reviews pose an integral part of Social CRM. However, polarity analysis, i.e., positive vs. negative opinion, fails to map the emotional mindset of customers. To complement existing Social CRM tools with a comprehensible, yet efficient way of measuring emotions towards brands, a model is presented to differentiate eight basic human emotions. Emotion terms get extracted and categorized review-wise by an eight dimensional emotion lexicon into eight dimensional feature vectors. These vectors train the random forest classifier to distinguish positive helpful from negative helpful reviews. The classifiers inherent ability to display single feature importance enables marketers to infer the importance of each basic emotion. The ability to measure the interrelationship of emotions towards brands equips marketers with a powerful tool to better understand consumers and to adapt CRM campaigns accordingly. Along with the technicalities of the model a way of interpreting results is presented.


Brands Emotions Online customer reviews Helpfulness Text mining Social CRM 


  1. 1.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)Google Scholar
  2. 2.
    Caruana, R., Niculescu-Mizil, A.: An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 161–168. ACM (2006)Google Scholar
  3. 3.
    Kapferer, J.-N.: The New Strategic Brand Management: Advanced Insights and Strategic Thinking. Kogan Page Publishers (2012)Google Scholar
  4. 4.
    Martin, L., Sintsova, V., Pearl, P.: Are influential writers more objective? An analysis of emotionality in review comments. In: Proceedings of the Companion Publication of the 23rd International Conference on World Wide Web Companion, pp. 799–804. International World Wide Web Conferences Steering Committee (2014)Google Scholar
  5. 5.
    Maynard, D., Bontcheva, K., Rout, D.: Challenges in developing opinion mining tools for social media. In: Proceedings of the@ NLP can u tag# usergeneratedcontent, pp. 15–22 (2012)Google Scholar
  6. 6.
    Scott, M., Alan, Z., Daniel, L.: The New Science of Customer Emotions. Harvard Business School Publishing Corporation (2015)Google Scholar
  7. 7.
    McAuley, J., Leskovec, J.: Hidden factors and hidden topics: understanding rating dimensions with review text. In: Proceedings of the 7th ACM Conference on Recommender Systems, pp. 165–172. ACM (2013)Google Scholar
  8. 8.
    Mohammad, S.M., Turney, P.D.: Crowdsourcing a word-emotion association lexicon. Comput. Intell. 29(3), 436–465 (2013)CrossRefGoogle Scholar
  9. 9.
    Plutchik, R.: A General Psychoevolutionary Theory of Emotion. In: Theories of Emotion, vol. 1 (1980)Google Scholar
  10. 10.
    Olaf, R., Rainer, A.: Social Customer Relationship Management: State of the Art and Learnings from Current Projects (2012)Google Scholar
  11. 11.
    Scherer, K.R.: What are emotions? And how can they be measured? Soc. Sci. Inf. 44(4), 695–729 (2005)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Katholische Universität Eichstätt-IngolstadtIngolstadtGermany

Personalised recommendations