M.A. Stankevich – Engineer, FRC «Computer Science and Control» of RAS (Moscow)

E-mail: stankevich@isa.ru

I.V. Smirnov – Ph.D.(Phys.-Math.), Head of Department, FRC «Computer Science and Control» of RAS (Moscow) E-mail: ivs@isa.ru

N.A. Ignatiev – Student, RUDN Univercity (Moscow)

E-mail: naignatiev@yandex.com

N.V. Kiselnikova – Ph.D.(Psych.), Head of Laboratory, Psychological Institute of Russian Academy of Education (Moscow) E-mail: nv.pirao@gmail.com

M.M. Danina – Ph.D.(Psych.), Senior Research Scientist, Psychological Institute of Russian Academy of Education (Moscow) E-mail: mdanina@yandex.ru

This work is devoted to the analysis of the Big Five personality model of users in social media by automatic processing of their social media profiles. To form the dataset, we asked VKontakte users to complete NEO-FFI questionnaire in order to reveal their level of neuroticism, extraversion, agreeableness, openness to experience, and conscientiousness. Then, we utilized the data from the personal pages of 165 users who granted permission to process their data to form the features and perform a multiclass classification task. On the basis of the obtained data set, a multi-class classification was made, the purpose of which was to automatically determine the level of expression of each of the five personal traits of users.

1. Gosling S.D., Rentfrow P.J., Swann Jr W.B. A very brief measure of the Big-Five personality domains // Journal of Research in personality. 2003. Т. 37. № 6. S. 504−528.
2. Ortigosa A., Carro R.M., Quiroga J.I. Predicting user personality by mining social interactions in Facebook // Journal of computer and System Sciences. 2014. Т. 80. № 1. S. 57−71.
3. Schwartz H.A. et al. Personality, gender, and age in the language of social media: The open-vocabulary approach // PloS one. 2013. Т. 8. № 9. S. e73791.
4. Costa P.T., McCrae R.R. NEO five-factor inventory (NEO-FFI). Odessa, FL: Psychological Assessment Resources. 1989.
5. Coppersmith G. et al. CLPsych 2015 shared task: Depression and PTSD on Twitter // Proc. of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. 2015. S. 31−39.
6. Yazdavar A.H. et al. Semi-supervised approach to monitoring clinical depressive symptoms in social media // Proc. of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. ACM. 2017. S. 1191−1198.
7. Jamil Z. Monitoring Tweets for Depression to Detect At-risk Users: dis. Université d'Ottawa/University of Ottawa. 2017.
8. De Choudhury M., Counts S., Horvitz E. Social media as a measurement tool of depression in populations // Proc. of the 5th Annual ACM Web Science Conference. ACM. 2013. S. 47−56.
9. Wang X. et al. A depression detection model based on sentiment analysis in micro-blog social network // Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, Berlin, Heidelberg. 2013. S. 201−213.
10. Cobb-Clark D.A., Schurer S. The stability of big-five personality traits // Economics Letters. 2012. Т. 115. № 1. S. 11−15.
11. Golbeck J. et al. Predicting personality from twitter // Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom). 2011. S. 149−156.
12. Pennebaker J.W., Francis M.E., Booth R.J. Linguistic inquiry and word count: LIWC 2001 // Mahway: Lawrence Erlbaum Associates. 2001. Т. 71.
13. Coltheart M. The MRC psycholinguistic database // The Quarterly Journal of Experimental Psychology. 1981. Т. 33. № 4. S. 497−505.
14. Pedregosa F. et al. Scikit-learn: Machine learning in Python // Journal of machine learning research. Oct. 2011. Т. 12. S. 2825−2830.