Having Fun?: Personalized Activity-Based Mood Prediction in Social Media

Chapter
Part of the Lecture Notes in Social Networks book series (LNSN)

Abstract

People engage in various activities and hobbies as a part of their work as well as for entertainment. Positivity and negativity attributes of a person’s mood and emotions are affected by the activity that they’re engaged in. In addition to that, time is also a fundamental contextual trigger for emotions as activities have been found to occur at particular time. An interesting question is can we design accurate personalized classifiers that can predict a person’s mood or emotions based on these features extracted from his/her posting in social media? Such a classifier would enable caretakers and health personnel to monitor people going through conditions such as depression as well as identifying people in a timely manner who may be prone to such conditions. This paper explores the design, implementation, and evaluation of such a classifier based on the data collected from Twitter. To do so, crowdworkers were first recruited through Amazon’s Mechanical Turk to label the dataset. A number of potential features are then explored to build a general classifier to automatically predict positivity or negativity of users’ tweets. These features include social engagement, gender, language and linguistic styles, and various psychological features. Then in addition to these features, LIWC is used to extract daily activities of users. Observations show how much activities and temporal nature of posting can be useful behavioral cues to develop a personalized classifier that improves the prediction accuracy of tweets of individual users as positive, negative, and neutral.

Keywords

Emotion and mood Personal activities Personalized classifier Twitter 

References

  1. 1.
    Gouveia R, Karapanos E (2013) Footprint tracker: supporting diary studies with lifelogging. In: Proceeding of the SIGCHI conference on human factors in computing systems, CHI ‘13, Paris, pp 2921–2930Google Scholar
  2. 2.
    Roshanaei M, Mishra S (2014) An analysis of positivity and negativity attributes of users in Twitter. In: Proceeding of ASONAM, pp 365–370Google Scholar
  3. 3.
    Rui L, Wang S, Deng H, Wang R, Chang KC (2012) Towards social user profiling: unified and discriminative influence model for inferring home locations. In: LinkKDD. Beijing, pp 1023–1031Google Scholar
  4. 4.
    Picard R (1995) Affective Computing, M.I.T Media Laboratory Perceptual Computing Section Technical Report, vol. 321, pp 1–26Google Scholar
  5. 5.
    Damasio AR (1994) Descartes’ error: emotion, reason and the human brain. Picador, Avon Books, A Division of The Hearst Corporation, New YorkGoogle Scholar
  6. 6.
    Marreiros G, Santos R, Ramos C, Neves J (2010) Context aware emotional model for group decision making. IEEE Trans Intell Syst 25(2):31–39CrossRefGoogle Scholar
  7. 7.
    Saari T, Kallinen K, Salminen M, Ravaja N, Yanev K (2008) A mobile system and application for facilitating emotional awareness in knowledge work teams. In: Hawaii international conference on system sciences, Waikoloa, pp 1–10Google Scholar
  8. 8.
    Wilson T, Wiebe J, Hoffmann P (2008) Recognizing contextual polarity in phrase-level sentiment analysis. Comput Linguist 35(3):399–433CrossRefGoogle Scholar
  9. 9.
    Vazire S, Gosling SD (2004) e-Perceptions: personality impressions based on personal websites. J Pers Soc Psychol 87(1):123–132CrossRefGoogle Scholar
  10. 10.
    Back M, Stopfer J, Vazire S, Gaddis S, Schmukle S, Egloff B, Gosling S (2010) Facebook profiles reflect actual personality, not self-idealization. Psychol Sci 21(3):372–374CrossRefGoogle Scholar
  11. 11.
    da Silva NFF et al (2014) Tweet sentiment analysis with classifier ensembles. Decis Support Syst 66(17):170–179CrossRefGoogle Scholar
  12. 12.
    Mohammad S, Kiritchenko S, Zhu X (2013) Nrc-Canada: building the state-of-the-art in sentiment analysis of tweets. In: Proceedings of the seventh international workshop on semantic evaluation exercises (SemEval-2013), Atlanta, Georgia, USAGoogle Scholar
  13. 13.
    Saif H, He Y, Alani H (2012) Semantic sentiment analysis of twitter. In: Proceedings of the 11th international conference on the semantic web—volume part I, ISWC’12, Springer-Verlag, Berlin, Heidelberg, pp 508–524Google Scholar
  14. 14.
    De Choudhury M, Counts S, Gamon M (2012) Not all moods re created equal! a exploring human emotional states in social media. In: Proceeding of international AAAI conference on weblogs and social media, Dublin, pp 66–73Google Scholar
  15. 15.
    Tchokni S, Eaghdha DOS, Quercia D (2014) Emotions and phrases: status symbols in social media. In: Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media Ann Arbor, pp~485–494Google Scholar
  16. 16.
    Park J, Barash V, Analytics M, Fink C, Cha M (2013) Emoticon style: interpreting differences in emoticons across cultures. In: Proceeding of international AAAI conference on weblogs and social media. Boston, pp 466–475Google Scholar
  17. 17.
    Park K, Lee S, Kim E, Park M, Park J, Cha M (2013) Mood and weather: feeling the heat?. In: Proceeding of international AAAI conference on weblogs and social media (Workshop), BostonGoogle Scholar
  18. 18.
    M. De Choudhury, S. Counts, E. Horvitz (2013) Predicting postpartum changes in emotion and behavior via social media. In: Proceeding of the SIGCHI conference on human factors in computing systems, New York, pp 3267–3276Google Scholar
  19. 19.
    Tausczik YR, Pennebaker JW (2009) The psychological meaning of words: LIWC and computerized text analysis methods. J Lang Soc Psychol 29(1):24–54CrossRefGoogle Scholar
  20. 20.
    Kotikalapudi R, Chellappan S, Montgomery F, Wunsch D, Lutzen K (2012) Associating depressive symptoms in college students with internet usage using real Internet data. IEEE Tech Soc Mag 31(4):73–80CrossRefGoogle Scholar
  21. 21.
    De Choudhury M, Gamon M, Counts S, Horvitz E (2013) Predicting depression via social media. In: Proceeding of international AAAI conference on weblogs and social media. Boston, pp 128–137Google Scholar
  22. 22.
    Park M, D. W. McDonald, Cha M (2013) Perception differences between the depressed and non-depressed users in Twitter. In: Proceeding of international AAAI conference on weblogs and social media, Boston, pp 476–485Google Scholar
  23. 23.
    Gross J (1998) The emerging field of emotion regulation: an integrative review. Rev Gen Psychol 2:271–299CrossRefGoogle Scholar
  24. 24.
    Pennebaker JW, Mehl MR, Niederhoffer KG (2003) Psychological aspects of natural language use: our words, ourselves. Annu Rev Psychol 54:547–577CrossRefGoogle Scholar
  25. 25.
    Fischer A, Manstead A (2000) The relation between gender and emotion in different cultures. In: Fischer A (ed) Gender and emotion: social psycholgical perspectives. Cambridge University Press, Cambridge, pp 71–94CrossRefGoogle Scholar
  26. 26.
    Rime B, Mesquita B, Philippot P, Boca S (1991) Beyond the emotional event: six studies on the social sharing of emotion. Cognit Emotion 5:435–465CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Mahnaz Roshanaei
    • 1
  • Richard Han
    • 1
  • Shivakant Mishra
    • 1
  1. 1.Department of Computer ScienceUniversity of ColoradoBoulderUSA

Personalised recommendations