Advertisement

Exploratory Analysis of Marketing and Non-marketing E-cigarette Themes on Twitter

  • Sifei Han
  • Ramakanth KavuluruEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10047)

Abstract

Electronic cigarettes (e-cigs) have been gaining popularity and have emerged as a controversial tobacco product since their introduction in 2007 in the U.S. The smoke-free aspect of e-cigs renders them less harmful than conventional cigarettes and is one of the main reasons for their use by people who plan to quit smoking. The US food and drug administration (FDA) has introduced new regulations early May 2016 that went into effect on August 8, 2016. Given this important context, in this paper, we report results of a project to identify current themes in e-cig tweets in terms of semantic interpretations of topics generated with topic modeling. Given marketing/advertising tweets constitute almost half of all e-cig tweets, we first build a classifier that identifies marketing and non-marketing tweets based on a hand-built dataset of 1000 tweets. After applying the classifier to a dataset of over a million tweets (collected during 4/2015 – 6/2016), we conduct a preliminary content analysis and run topic models on the two sets of tweets separately after identifying the appropriate numbers of topics using topic coherence. We interpret the results of the topic modeling process by relating topics generated to specific e-cig themes. We also report on themes identified from e-cig tweets generated at particular places (such as schools and churches) for geo-tagged tweets found in our dataset using the GeoNames API. To our knowledge, this is the first effort that employs topic modeling to identify e-cig themes in general and in the context of geo-tagged tweets tied to specific places of interest.

Keywords

Topic Modeling Sentiment Analysis Convolutional Neural Network Electronic Cigarette Electronic Nicotine Delivery System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

We thank anonymous reviewers for constructive criticism that helped improve the presentation of this paper. This research was supported by the National Center for Research Resources and the National Center for Advancing Translational Sciences, US National Institutes of Health (NIH), through Grant UL1TR000117 and the Kentucky Lung Cancer Research Program through Grant PO2-415-1400004000-1. The content of this paper is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.

References

  1. 1.
    Agarwal, A., Xie, B., Vovsha, I., Rambow, O., Passonneau, R.: Sentiment analysis of twitter data. In: Proceedings of the Workshop on Languages in Social Media, pp. 30–38. Association for Computational Linguistics (2011)Google Scholar
  2. 2.
    Barrington-Trimis, J.L., Urman, R., Berhane, K., Unger, J.B., Cruz, T.B., Pentz, M.A., Samet, J.M., Leventhal, A.M., McConnell, R.: E-cigarettes and future cigarette use. Pediatrics 138, e20160379 (2016)CrossRefGoogle Scholar
  3. 3.
    Blei, D.M., Lafferty, J.D.: Topic models. In: Srivastava, A., Sahami, M. (eds.) Text Mining:Classification, Clustering, and Applications, chapter 4, pp. 71–93. CRC Press, Chapman and Hall (2009)Google Scholar
  4. 4.
    Centers for Disease Control. E-cigarette use triples among middle and high school students in just one year. http://www.cdc.gov/media/releases/2015/p0416-e-cigarette-use.html
  5. 5.
    Chaney, A.J.-B., Blei, D.M.: Visualizing topic models. In: International Conference of Weblogs and Social Media, ICWSM 2012 (2012)Google Scholar
  6. 6.
    Chen, I.-L., et al.: FDA summary of adverse events on electronic cigarettes. Nicotine Tob. Res. 15(2), 615–616 (2013)CrossRefGoogle Scholar
  7. 7.
    Cheng, X., Yan, X., Lan, Y., Guo, J.: BTM: Topic modeling over short texts. Knowl. Data Eng. IEEE Trans. 26(12), 2928–2941 (2014)CrossRefGoogle Scholar
  8. 8.
    Chu, K.-H., Unger, J.B., Allem, J.-P., Pattarroyo, M., Soto, D., Cruz, T.B., Yang, H., Jiang, L., Yang, C.C.: Diffusion of messages from an electronic cigarette brand to potential users through twitter. PloS One 10(12), e0145387 (2015)CrossRefGoogle Scholar
  9. 9.
    Cole-Lewis, H., Pugatch, J., Sanders, A., Varghese, A., Posada, S., Yun, C., Schwarz, M., Augustson, E.: Social listening: A content analysis of e-cigarette discussions on twitter. J. Medi. Int. Res. 17(10), e243 (2015)Google Scholar
  10. 10.
    Cole-Lewis, H., Varghese, A., Sanders, A., Schwarz, M., Pugatch, J., Augustson, E.: Assessing electronic cigarette-related tweets for sentiment and content using supervised machine learning. J. Med. Int. Res. 17(8), e208 (2015)Google Scholar
  11. 11.
    Culotta, A., Kumar, N.R., Cutler, J.: Predicting the demographics of twitter users from website traffic data. In: Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 72–78 (2015)Google Scholar
  12. 12.
    Etter, J.-F., Bullen, C., Flouris, A.D., Laugesen, M., Eissenberg, T.: Electronic nicotine delivery systems: a research agenda. Tob. Control 20(3), 243–248 (2011)CrossRefGoogle Scholar
  13. 13.
    Food and Drug Administration, HHS et al.: Deeming tobacco products to be subject to the federal food, drug, and cosmetic act, as amended by the family smoking prevention and tobacco control act; restrictions on the sale and distribution of tobacco products and required warning statements for tobacco products. final rule. Federal Reg. 81(90), 28973 (2016)Google Scholar
  14. 14.
    Godea, A.K., Caragea, C., Bulgarov, F.A., Ramisetty-Mikler, S.: An analysis of twitter data on e-cigarette sentiments and promotion. In: Holmes, J.H., Bellazzi, R., Sacchi, L., Peek, N. (eds.) AIME 2015. LNCS (LNAI), vol. 9105, pp. 205–215. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-19551-3_27 CrossRefGoogle Scholar
  15. 15.
    Han, S., Kavuluru, R.: On assessing the sentiment of general tweets. In: Barbosa, D., Milios, E. (eds.) CANADIAN AI 2015. LNCS (LNAI), vol. 9091, pp. 181–195. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-18356-5_16 Google Scholar
  16. 16.
    Hoffman, M., Bach, F.R., Blei, D.M.: Online learning for latent Dirichlet allocation. Adv. Neural Inf. Proc. Syst. 21, 856–864 (2010)Google Scholar
  17. 17.
    Hong, L., Davison, B.D.: Empirical study of topic modeling in twitter. In: Proceedings of the 1st Workshop on Social Media Analytics, pp. 80–88. ACM (2010)Google Scholar
  18. 18.
    Huang, J., Kornfield, R., Szczypka, G., Emery, S.L.: A cross-sectional examination of marketing of electronic cigarettes on twitter. Tob. Control 23, 26–30 (2014). (suppl 3)CrossRefGoogle Scholar
  19. 19.
    Kavuluru, R., Sabbir, A.: Toward automated e-cigarette surveillance: Spotting e-cigarette proponents on Twitter. J. Biomed. Inf. 61, 19–26 (2016)CrossRefGoogle Scholar
  20. 20.
    Kim, A.E., Hopper, T., Simpson, S., Nonnemaker, J., Lieberman, A.J., Hansen, H., Guillory, J., Porter, L.: Using twitter data to gain insights into e-cigarette marketing and locations of use: An infoveillance study. J. Med. Int. Res. 17(11), e251 (2015)Google Scholar
  21. 21.
    Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751, October 2014Google Scholar
  22. 22.
    Klein, E.G., Berman, M., Hemmerich, N., Carlson, C., Htut, S., Slater, M.: Online e-cigarette marketing claims: A systematic content and legal analysis. Tob. Regul. Sci. 2(3), 252–262 (2016)CrossRefGoogle Scholar
  23. 23.
    Landis, J., Koch, G.: The measurement of observer agreement for categorical data. Biometrics 33(1), 159–174 (1977)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Levy, D.T., Cummings, K.M., Villanti, A.C., Niaura, R., Abrams, D.B., Fong, G.T., Borland, R.: A framework for evaluating the public health impact of e-cigarettes and other vaporized nicotine products. Addiction (2016)Google Scholar
  25. 25.
    Liu, W., Ruths, D.: What’s in a name? using first names as features for gender inferencein twitter. In: Proceedings of the AAAI Spring Symposium: AnalyzingMicrotext, pp. 10–16 (2013)Google Scholar
  26. 26.
    Malik, S., Smith, A., Hawes, T., Papadatos, P., Li, J., Dunne, C., Shneiderman, B.: Topicflow: visualizing topic alignment of twitter data over time. In: Proceedings of the 2013 IEEE/ACM International Conference Onadvances in Social Networks Analysis and Mining, pp. 720–726. ACM (2013)Google Scholar
  27. 27.
    Martin, E., Clapp, P.W., Rebuli, M.E., Pawlak, E.A., Glista-Baker, E.E., Benowitz, N.L., Fry, R.C., Jaspers, I.: E-cigarette use results in suppression of immune and inflammatory-response genes in nasal epithelial cells similar to cigarette smoke. Am. J. Physiol. Lung Cell. Mol. Physiol. 311, L135–L144 (2016)Google Scholar
  28. 28.
    McNeill, A., Brose, L., Calder, R., Hitchman, S., Hajek, P., McRobbie, H.: E-cigarettes: an evidence update. Report from Public Health England (2015)Google Scholar
  29. 29.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 21, 3111–3119 (2013)Google Scholar
  30. 30.
    Myslín, M., Zhu, S.-H., Chapman, W., Conway, M.: Using twitter to examine smoking behavior and perceptions of emerging tobacco products. J. Med. Int. Res. 15(8), e174 (2013)Google Scholar
  31. 31.
    Nguyen, D., Gravel, R., Trieschnigg, D., Meder, T.: how old do you think i am? a study of language and age in twitter. In: Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media (ICWSM), pp. 439–448 (2013)Google Scholar
  32. 32.
    OCallaghan, D., Greene, D., Carthy, J., Cunningham, P.: An analysis of the coherence of descriptors in topic modeling. Expert Syst. Appl. 42(13), 5645–5657 (2015)CrossRefGoogle Scholar
  33. 33.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  34. 34.
    Pew Research Internet Project. Part 1: Teens and social media use. http://www.pewinternet.org/2013/05/21/part-1-teens-and-social-media-use/
  35. 35.
    Rios, A., Kavuluru, R.: Convolutional neural networks for biomedical text classification:application in indexing biomedical articles. In: Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics, pp. 258–267. ACM (2015)Google Scholar
  36. 36.
    Rudy, S., Durmowicz, E.: Electronic nicotine delivery systems: overheating, fires andexplosions. Tob. Control (2016) (in press)Google Scholar
  37. 37.
    Singh, T., Arrazola, R., Corey, C., Husten, C., Neff, L., Homa, D., King, B.: Tobacco use among middle and high school students - United States, 2011–2015. MMWR Morb. Mortal. Wkly. Rep. 65(14), 361–367 (2016)CrossRefGoogle Scholar
  38. 38.
    Wilson, E.B.: Probable inference, the law of succession, and statistical inference. J. Am. Statist. Assoc. 22(158), 209–212 (1927)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Division of Biomedical Informatics, Department of Internal MedicineUniversity of KentuckyLexingtonUSA
  2. 2.Department of Computer ScienceUniversity of KentuckyLexingtonUSA

Personalised recommendations