IDENTIFICATION OF MBTI (MYERS-BRIGGS TYPE INDEX) HUMAN TYPE USING TEXT ON SOCIAL NETWORKS BASED MACHINE LEARNING

This study aims to create a classifier using machine learning methods that determine the psychological type of people based on the text published on social networks according to the Myers-Briggs Type Index classification. The article is based on the implementation of automation of the task of determining the personality type using machine learning, with an explanation for determining the characteristics of a person using the MBTI personality indicator. The methods of logistic regression, random forest and support vector machines were used, and a literary analysis of similar works was carried out. The article presents the progress of research work and the results of each classifier, as well as an analysis of the approaches used. In the context of the current quarantine restrictions, such studies can be of great help in the selection of personnel in companies due to the transition of people to an online format of work, since the study involves determining the personal qualities of people based on their posts in social networks. In this paper, the most effective machine learning algorithms for the Kazakh language, which are simple to use and do not require a lot of computing power, were used and, accordingly, the results of the work for each method were presented, among these methods, the accuracy and reliability of the classifier for the Kazakh language by the method of support vectors were at a good level.

1. Stivenson M. Vvedenie v nejrolingvisticheskoe programmirovanie [Introduction to neuro-linguistic programming] [in Russian]

2. Rawlings D., Ciancarelli V. (1997) Music preference and the five-factor model of the neo personality inventory. Psychology of Music. P. 120–132

3. Ferwerda B., Schedl M., Tkalcic M. (2015) Personality & emotional states: Understanding users' music listening needs. UMAP 2015 Extended Proceedings

4. Ferwerda B., Schedl M. (2014) Enhancing music recommender systems with personality information and emotional states: A proposal. Proc. EMPIRE workshop.

5. Celli F., Bruni E., Lepri B. (2014) Automatic personality and interaction style recognition from Facebook profile pictures. Proceedings of the ACM International Conference on Multimedia. P. 1101–1104

6. Cristani M., Vinciarelli A., Segalin C., Perina A. (2013) Unveiling the multimedia unconscious: Implicit cognitive processes and multimedia content analysis. Proceedings of the 21st ACM international conference on Multimedia.

7. Pennebaker J.W., King L.A. (1999) Linguistic Styles: Language Use as an Individual Difference. Personality and Social Psychology. 77(6). P. 1296–1312

8. Hernandez R., Knight I.S. (2017) Predicting Myers-Briggs Type Indicator with Text Classification. 31st Conference on Neural Information Processing Systems, NIPS.

9. Gavrilescu M. (2015) Study on determining the Myers-Briggs personality type based on individual's handwriting. The 5th IEEE International Conference on E-Health and Bioengineering.

10. Majumder N., Poria S., Gelbukh A., Cambria E. (2017) Deep learning-based document modeling for personality detection from text. IEEE Computer Society, IEEE Intelligent Systems. https://sentic.net/deep-learning-based-personality-detection.pdf

11. Komisin M., Guinn C. (2012) Identifying personality types using document classification methods. Proceedings of the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25. P. 232–237

12. Ingersoll G.S., Morton T.S., Ferris E.L. (2015) Obrabotka nestrukturirovannykh tekstov. Poisk, organizacziya i manipulirovanie. / Per. s angl. Slinkin A.A. M.: DMK Press. – 414 s. [Processing of unstructured texts. Search, organization, and manipulation. / Translated from English. Slinkin A. A. M.: DMK Press - 414 p.] [in Russian]

13. Harrington R., Loffredo D.A. (2010) MBTI personality type and other factors that relate to preference for online versus face-to-face instruction. The Internet and Higher Education. Volume 13, Issues 1–2, pp. 89-95

14. Verhoeven B., Daelemans W., Plank B. (2016) TwiSty: A Multilingual Twitter Stylometry Corpus for Gender and Personality Profiling. Proceedings of the 10th edition of the Language Resources and Evaluation Conference European Language Resources Association (ELRA)

15. Friedman J.H. (2001) Greedy function approximation: A gradient boosting machine. The Annalls of Statistics. 29(5). 1189–1232.

16. Gallo F.R., Simari G.I., Martinez M.V., Falappa M.A. (2020) Predicting user reactions to Twitter feed content based on personality type and social cues. Future Generation Computer Systems, volume 110, p. 918-930.

17. Bencke L., Cechinel C., Munoz R. (2020) Automated classification of social network messages into Smart Cities dimensions. Future Generation Computer Systems, volume 109, p. 218-237.