Auto-Tracking Controversial Topics in Social-Media-Based Customer Dialog: A Case Study on Starbucks

  • Bei YuEmail author
  • Yihan Yu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10766)


This study proposed and validated a topic modeling-based approach for auto-tracking customer dialog on social media, using Starbucks as a case study because of its pioneering social media practice in service industry. A topic model was fit based on nearly 150,000 customer comments posted to Starbucks’ Facebook page in 2013. This model was able to identify not only business-related topics, such as customer responses to marketing campaigns, but also controversial topics regarding community involvement and corporate social responsibility, such as gay, gun, and government. Guided by this topic model, each topic’s evolving dynamics and patterns of user participation were further revealed, providing a bird’s-eye view of the topics and their evolution. The case study has demonstrated that the proposed approach can effectively track the main themes in the customer dialog on social media, zoom in on the controversial topics, measure their time spans, and locate the participants and the vocal activists. Such information would be valuable input for companies to design their intervention strategies and evaluate the outcomes in social media discussions.


Topic modeling Text mining Customer dialog Social media 


  1. Bíró, I., Siklósi, D., Szabó, J., Benczúr, A.A.: Linked latent dirichlet allocation in web spam filtering. In: Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web, pp. 37–40. ACM, New York (2009)Google Scholar
  2. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)zbMATHGoogle Scholar
  3. Brown, J., Broderick, A.J., Lee, N.: Word of mouth communication within online communities: Conceptualizing the online social network. J. Interact. Mark. 21(3), 2–20 (2007)CrossRefGoogle Scholar
  4. Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J.L., Blei, D.M.: Reading tea leaves: how humans interpret topic models. In: Advances in neural information processing systems, pp. 288–296 (2009)Google Scholar
  5. Chua, A.Y.K., Banerjee, S.: Customer knowledge management via social media: the case of Starbucks. Journal of Knowledge Management 17(2), 237–249 (2013)CrossRefGoogle Scholar
  6. CNN: Starbucks CEO holds his ground on gay marriage (2013). Accessed 26 Mar 2013
  7. Coombs, W.T.: Protecting organization reputations during a crisis: the development and application of situational crisis communication theory. Corp. Reput. Rev. 10(3), 163–176 (2007)CrossRefGoogle Scholar
  8. Gallaugher, J., Ransbotham, S.: Social media and customer dialog management at Starbucks. MIS Q. Exec. 9(4), 197–212 (2010)Google Scholar
  9. Greene, D., O’Callaghan, D., Cunningham, P.: How many topics? stability analysis for topic models. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014. LNCS (LNAI), vol. 8724, pp. 498–513. Springer, Heidelberg (2014). Google Scholar
  10. Hays, S., Page, S.J., Buhalis, D.: Social media as a destination marketing tool: its use by national tourism organisations. Curr. Issues Tour. 16(3), 211–239 (2013)CrossRefGoogle Scholar
  11. He, W., Zha, S., Li, L.: Social media competitive analysis and text mining: a case study in the pizza industry. Int. J. Inf. Manage. 33(3), 464–472 (2013)CrossRefGoogle Scholar
  12. Holcomb, J., Upchurch, R., Okumus, F.: Corporate social responsibility: what are top hotel companies reporting? Int. J. Contemp. Hosp. Manag. 19(6), 461–475 (2007)CrossRefGoogle Scholar
  13. Keyling, T., Jünger, J.: Facepager (version, f.e. 3.3). An application for generic data retrieval through APIs (2013).
  14. Kim, E.: The role of social media in crisis communication - a case study of Starbucks (thesis) (2013).
  15. Kwok, L., Yu, B.: Spreading social media messages on Facebook: an analysis of restaurant business-to-consumer communications. Cornell Hosp. Q. 54(1), 84–94 (2013)CrossRefGoogle Scholar
  16. Kwok, L., Zhang, F., Huang, Y., Yu, B., Maharabhushanam, P., Rangan, K.: Documenting business-to-consumer (B2C) communications on Facebook: what have changed among restaurants and consumers? Worldwide Hosp. Tour. Themes 7(3), 283–294 (2015). CrossRefGoogle Scholar
  17. Lazarsfeld, P.F., Berelson, B., Gaudet, H.: The People’s Choice; How the Voter Makes Up His Mind in a Presidential Campaign, 3rd edn. Columbia University Press, New York (1968)Google Scholar
  18. Leonard, P.: Mining large datasets for the humanities (2014).
  19. Mangold, W.G., Faulds, D.J.: Social media: the new hybrid element of the promotion mix. Bus. Horiz. 52(4), 357–365 (2009)CrossRefGoogle Scholar
  20. Maskeri, G., Sarkar, S., Heafield, K.: Mining business topics in source code using latent dirichlet allocation. In: Proceedings of the 1st India Software Engineering Conference, pp. 113–120. ACM, New York (2008)Google Scholar
  21. McCallum, A.: MALLET: A Machine Learning for Language Toolkit (2002).
  22. Men, L.R., Tsai, W.H.S.: How companies cultivate relationships with publics on social network sites: evidence from China and the United States. Public Relat. Rev. 38(5), 723–730 (2012)CrossRefGoogle Scholar
  23. Mustafaraj, E., Finn, S., Whitlock, C., Metaxas, P.T.: Vocal minority versus silent majority: discovering the opinions of the long tail. In: 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third International Conference on Social Computing (SocialCom), pp. 103–10. IEEE (2011)Google Scholar
  24. Timian, A., Rupcic, S., Kachnowski, S., Luisi, P.: Do patients “like” good care? measuring hospital quality via Facebook. Am. J. Med. Qual. 28(5), 374–382 (2013)CrossRefGoogle Scholar
  25. Veil, S.R.: Crisis communication and agrosecurity: organizational learning in a high-risk environment. Ph.D. thesis (2007).
  26. Waters, R.D., Burnett, E., Lamm, A., Lucas, J.: Engaging stakeholders through social networking: how nonprofit organizations are using Facebook. Public Relat. Rev. 35(2), 102–106 (2009)CrossRefGoogle Scholar
  27. West, T.: Starbucks tops social engagement study: what can your biz learn? - vote for the best company in Albuquerque’s business competition. Accessed 27 May 2015
  28. Yang, T.-I., Andrew, J.T., Mihalcea, R.: Topic modeling on historical newspapers. In: Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, pp. 96–104 (2011)Google Scholar
  29. Zou, H., Chen, H.M., Dey, S.: Understanding library user engagement strategies through large-scale Twitter analysis. In: 2015 IEEE First International Conference on Big Data Computing Service and Applications (BigDataService), pp. 361–370 (2015)Google Scholar
  30. Lewandowsky, S., Ecker, U.K.H., Seifert, C.M., Schwarz, N., Cook, J.: Misinformation and its correction: continued influence and successful debiasing. Psychol. Sci. Public Interest 13(3), 106–131 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Syracuse UniversitySyracuseUSA

Personalised recommendations