Spiteful, One-Off, and Kind: Predicting Customer Feedback Behavior on Twitter

  • Agus SulistyaEmail author
  • Abhishek Sharma
  • David Lo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10047)


Social media provides a convenient way for customers to express their feedback to companies. Identifying different types of customers based on their feedback behavior can help companies to maintain their customers. In this paper, we use a machine learning approach to predict a customer’s feedback behavior based on her first feedback tweet. First, we identify a few categories of customers based on their feedback frequency and the sentiment of the feedback. We identify three main categories: spiteful, one-off, and kind. Next, we build a model to predict the category of a customer given her first feedback. We use profile and content features extracted from Twitter. We experiment with different algorithms to create a prediction model. Our study shows that the model is able to predict different types of customers and perform better than a baseline approach in terms of precision, recall, and F-measure.


Social media Customer relationship management Machine learning 



This research is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its International Research Centres in Singapore Funding Initiative, and PT Telekomunikasi Indonesia (Telkom).


  1. 1.
  2. 2.
    Ajmera, J., Ahn, H.i., Nagarajan, M., Verma, A., Contractor, D., Dill, S., Denesuk, M.: A CRM system for social media: challenges and experiences. In: Proceedings of the 22nd international conference on World Wide Web, pp. 49–58. International World Wide Web Conferences Steering Committee (2013)Google Scholar
  3. 3.
    Arapakis, I., Cambazoglu, B.B., Lalmas, M.: On the feasibility of predicting news popularity at cold start. In: Aiello, L.M., McFarland, D. (eds.) SocInfo 2014. LNCS, vol. 8851, pp. 290–299. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-13734-6_21 Google Scholar
  4. 4.
    Bhatia, S., Li, J., Peng, W., Sun, T.: Monitoring and analyzing customer feedback through social media platforms for identifying and remedying customer problems. In: Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 1147–1154. ACM (2013)Google Scholar
  5. 5.
    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
  6. 6.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)Google Scholar
  7. 7.
    Chen, J., Cypher, A., Drews, C., Nichols, J.: CrowdE: filtering tweets for direct customer engagements. In: ICWSM, Citeseer (2013)Google Scholar
  8. 8.
    Dev, H., Ali, M.E., Mahmud, J., Sen, T., Basak, M., Paul, R.: A real-time crowd-powered testbed for content assessment of potential social media posts. In: Liu, T.-Y., Scollon, C.N., Zhu, W. (eds.) SocInfo 2015. LNCS, vol. 9471, pp. 136–152. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-27433-1_10 CrossRefGoogle Scholar
  9. 9.
    Einwiller, S.A., Steilen, S.: Handling complaints on social network sites-an analysis of complaints and complaint responses on facebook and twitter pages of large us companies. Public Relations Rev. 41(2), 195–204 (2015)CrossRefGoogle Scholar
  10. 10.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  11. 11.
    Huang, P.J.: Classication of imbalanced data using synthetic over-sampling techniques (2015)Google Scholar
  12. 12.
    Jhamtani, H., Chhaya, N., Karwa, S., Varshney, D., Kedia, D., Gupta, V.: Identifying suggestions for improvement of product features from online product reviews. In: Liu, T.-Y., Scollon, C.N., Zhu, W. (eds.) SocInfo 2015. LNCS, vol. 9471, pp. 112–119. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-27433-1_8 CrossRefGoogle Scholar
  13. 13.
    Meilă, M., Heckerman, D.: An experimental comparison of several clustering and initialization methods. In: Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, pp. 386–395. Morgan Kaufmann Publishers Inc. (1998)Google Scholar
  14. 14.
    Millard, N.J.: Serving the social customer: how to look good on the social dance floor. In: Nah, F.F.-H., Tan, C.-H. (eds.) HCIB 2015. LNCS, vol. 9191, pp. 165–174. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-20895-4_16 CrossRefGoogle Scholar
  15. 15.
    On, B.W., Lim, E.P., Jiang, J., Purandare, A., Teow, L.N.: Mining interaction behaviors for email reply order prediction. In: International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 306–310. IEEE (2010)Google Scholar
  16. 16.
    Pennacchiotti, M., Popescu, A.M.: A machine learning approach to twitter user classification. ICWSM 11(1), 281–288 (2011)Google Scholar
  17. 17.
    Rangnani, S., Susheela Devi, V., Narasimha Murty, M.: Autoregressive model for users’ retweeting profiles. In: Liu, T.-Y., Scollon, C.N., Zhu, W. (eds.) SocInfo 2015. LNCS, vol. 9471, pp. 178–193. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-27433-1_13 CrossRefGoogle Scholar
  18. 18.
    Tian, Y., Lo, D., Xia, X., Sun, C.: Automated prediction of bug report priority using multi-factor analysis. Empirical Softw. Eng. 20(5), 1354–1383 (2015)CrossRefGoogle Scholar
  19. 19.
    Van Hulse, J., Khoshgoftaar, T.M., Napolitano, A.: Experimental perspectives on learning from imbalanced data. In: Proceedings of the 24th International Conference on Machine Learning, pp. 935–942. ACM (2007)Google Scholar
  20. 20.
    Van Vlasselaer, V., Eliassi-Rad, T., Akoglu, L., Snoeck, M., Baesens, B.: Afraid: fraud detection via active inference in time-evolving social networks. In: Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015, pp. 659–666. ACM (2015)Google Scholar
  21. 21.
    Xia, X., Lo, D., Shihab, E., Wang, X., Yang, X.: ELBlocker: predicting blocking bugs with ensemble imbalance learning. Inf. Softw. Technol. 61, 93–106 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Human Capital CenterPT Telekomunikasi IndonesiaBandungIndonesia
  2. 2.School of Information SystemsSingapore Management UniversitySingaporeSingapore

Personalised recommendations