ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2023-23-2-279-288ntv-366Research ArticleКОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИCOMPUTER SCIENCEПредсказание результатов 16-факторного теста Р. Кеттелла на основе анализа текстовых постов пользователей социальной сетиPredicting the results of the 16-factor R. Cattell test based on the analysis of text posts of social network usershttps://orcid.org/0000-0002-3479-0085ОлисеенкоВ. Д.OliseenkoV. D.

Олисеенко Валерий Дмитриевич — младший научный сотрудник

Санкт-Петербург, 199178

sc 57219554703

Valerii D. Oliseenko — Junior Researcher

Saint Petersburg, 199178

sc 57219554703

vdo@dscs.prohttps://orcid.org/0000-0002-5476-3025АбрамовМ. В.AbramovM. V.

Абрамов Максим Викторович — кандидат технических наук, руководитель лаборатории, старший научный сотрудник

Санкт-Петербург, 199178

sc 56938320500

Maxim V. Abramov — PhD, Head of Laboratory, Senior Researcher

Saint Petersburg, 199178

sc 56938320500

mva@dscs.proСанкт-Петербургский Федеральный исследовательский центр Российской академии наукРоссияSt. Petersburg Federal Research Center of the Russian Academy of SciencesRussian Federation202319122024232279288Copyright © Олисеенко В.Д., Абрамов М.В., 20242024Олисеенко В.Д., Абрамов М.В.Oliseenko V.D., Abramov M.V.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/366

Предмет исследования. Исследована возможность автоматизации предсказания по небольшому набору данных оценки выраженности психологических особенностей по 16-факторному личностному тесту Р. Кеттелла пользователей социальной сети на основе анализа публикуемых ими на своей странице текстовых постов. Метод. Предложенный новый метод автоматизации оценки выраженности психологических особенностей по 16-факторному личностному тесту Р. Кеттелла включает в себя языковые модели и нейронные сети. Реализация метода предусматривает несколько шагов. На первом шаге происходит извлечение из аккаунтов пользователей социальной сети текстовых постов, их предобработка с помощью языковой модели RuBERT и ранее обученной достроенной над ней полносвязной нейронной сети. Итогом этого шага является нормализованное эмпирическое распределение постов по ранее введенным классам по каждому пользователю. Впоследствии на основе распределения постов пользователей производится оценка выраженности психологических особенностей пользователя с использованием метода опорных векторов, случайного леса и наивного байесовского классификатора. Основные результаты. Финальный набор данных для построения моделей и дальнейшего тестирования их работы составлен из 183 респондентов, прошедших тест Р. Кеттелла, со ссылками на их открытые аккаунты в социальной сети. Построены классификаторы, предсказывающие результаты для шести факторов (A, B, F, I, N, Q1) 16-факторного личностного теста Р. Кеттелла. Практическая значимость. Полученные результаты могут найти применение при создании прототипа автоматизированной системы предсказания оценки выраженности психологических особенностей пользователей социальной сети. Результаты работы полезны в прикладных и исследовательских системах, связанных с маркетингом, психологией и социологией, а также в области защиты пользователей от социоинженерных атак.

We investigated the possibility of automating the prediction of the 16-factor personality traits by R. Cattell from text posts of social media users. The proposed new method of automating the evaluation of R. Kettell’s 16-factor personality test traits includes language models and neural networks. Implementation of the method involves several steps. At the first step text posts are extracted from user accounts of social media, pre-processed with language model RuBERT and previously trained over a full-connected neural network. The result of this step is a normalized empirical distribution of the posts by the previously introduced classes for each user. Subsequently, based on the distribution of user posts the evaluation of the expression of psychological features of the user is made with the help of support vector machine, random forest and Naive Bayesian classifier. The final data set for model building and further testing their performance was made up of 183 respondents who took the R. Cattell test, with links to their public social media accounts. Classifiers predicting results for six factors (A, B, F, I, N, Q1) of R. Cattells 16-factor personality test were constructed. The results can be used to create a prototype of automated system for predicting the severity of psychological features of social media users. Results of work are useful in the applied and research systems connected with marketing, psychology and sociology, and also in the field of protection of users from social engineering attacks.

социальные сетиклассификация текстовискусственный интеллект16-факторный тест Р. Кеттелламашинное обучениенейронные сетиonline social networkstext classificationartificial intelligencesixteen personality factor questionnairemachine learningneural networksРабота выполнена в рамках проекта по государственному заданию СПБ ФИЦ РАН № FFZF-2022-0003; при финансовой поддержке РФФИ, проект № 20-07-00839; при финансовой поддержке гранта Президента Российской Федерации МK5237.2022.1.6The research was carried out in the framework of the project on state assignment SPC RAS No. FFZF-2022-0003, with the financial support of the RFBR (No. 20-07-00839), with the financial support of the grant of the President of the Russian Federation MK 5237.2022.1.6.ReferencesVander Shee B.A., Peltier J., Dahl A.J. Antecedent consumer factors, consequential branding outcomes and measures of online consumer engagement: Current research and future directions // Journal of Research in Interactive Marketing. 2020. V. 14. N 2. P. 239–268. https://doi.org/10.1108/JRIM-01-2020-0010Vander Shee B.A., Peltier J., Dahl A.J. Antecedent consumer factors, consequential branding outcomes and measures of online consumer engagement: Current research and future directions. Journal of Research in Interactive Marketing, 2020, vol. 14, no. 2, pp. 239–268. https://doi.org/10.1108/JRIM-01-2020-0010Fayaz A., Muhammad Z.T., Ayaz A. The Big Five dyad congruence and compulsive buying: A case of service encounters // Journal of Retailing and Consumer Services. 2022. V. 68. P. 103007. https://doi.org/10.1016/j.jretconser.2022.103007Fayaz A., Muhammad Z.T., Ayaz A. The Big Five dyad congruence and compulsive buying: A case of service encounters. Journal of Retailing and Consumer Services, 2022, vol. 68, pp. 103007. https://doi.org/10.1016/j.jretconser.2022.103007Shanahan T., Tran T.P., Taylor E.C. Getting to know you: Social media personalization as a means of enhancing brand loyalty and perceived quality // Journal of Retailing and Consumer Services. 2019. N 47. P. 57–65. https://doi.org/10.1016/j.jretconser.2018.10.007Shanahan T., Tran T.P., Taylor E.C. Getting to know you: Social media personalization as a means of enhancing brand loyalty and perceived quality. Journal of Retailing and Consumer Services, 2019, no. 47, pp. 57–65. https://doi.org/10.1016/j.jretconser.2018.10.007Woods S.A., Mustafa M.J., Anderson N., Sayer B. Innovative work behavior and personality traits: Examining the moderating effects of organizational tenure // Journal of Managerial Psychology. 2018. V. 33. N 1. P. 29–42. https://doi.org/10.1108/JMP-01-2017-0016Woods S.A., Mustafa M.J., Anderson N., Sayer B. Innovative work behavior and personality traits: Examining the moderating effects of organizational tenure. Journal of Managerial Psychology, 2018, vol. 33, no. 1, pp. 29–42. https://doi.org/10.1108/JMP-01-2017-0016Bouiri O., Lotfi S., Talbi M. Correlative study between personality traits, student mental skills and educational outcomes // EducationSciences. 2021. V. 11. N 4. P. 153. https://doi.org/10.3390/educsci11040153Bouiri O., Lotfi S., Talbi M. Correlative study between personality traits, student mental skills and educational outcomes. EducationSciences, 2021, vol. 11, no. 4, pp. 153. https://doi.org/10.3390/educsci11040153Chekalev A.A., Khlobystova A.O., Tulupyeva T.V. Applicant’s decision support system for choosing the direction of study // Proc. of the XXV International Conference on Soft Computing and Measurements (SCM). 2022. P. 226–228. https://doi.org/10.1109/SCM55405.2022.9794902Chekalev A.A., Khlobystova A.O., Tulupyeva T.V. Applicant’s decision support system for choosing the direction of study. Proc. of the XXV International Conference on Soft Computing and Measurements (SCM), 2022, pp. 226–228. https://doi.org/10.1109/SCM55405.2022.9794902Stoliarova V.F., Tulupyev A.L. Cumulative mean function of public posting episodes in the online media with regard to user’s digital traces: Limited data on publications dates and profile data // Proc. of the XXV International Conference on Soft Computing and Measurements (SCM). 2022. P. 25–27. https://doi.org/10.1109/SCM55405.2022.9794894Stoliarova V.F., Tulupyev A.L. Cumulative mean function of public posting episodes in the online media with regard to user’s digital traces: Limited data on publications dates and profile data. Proc. of the XXV International Conference on Soft Computing and Measurements (SCM), 2022, pp. 25–27. https://doi.org/10.1109/SCM55405.2022.9794894Thielmann I., Spadaro G., Balliet D. Personality and prosocial behavior: A theoretical framework and meta-analysis // Psychological Bulletin. 2020. V. 146. N 1. P. 30–90. https://doi.org/10.1037/bul0000217Thielmann I., Spadaro G., Balliet D. Personality and prosocial behavior: A theoretical framework and meta-analysis. Psychological Bulletin, 2020, vol. 146, no. 1, pp. 30–90. https://doi.org/10.1037/bul0000217Clark C., Davila A., Regis M., Kraus S. Predictors of COVID-19 voluntary compliance behaviors: An international investigation // Global Transitions. 2020. V. 2. P. 76–82. https://doi.org/10.1016/j.glt.2020.06.003Clark C., Davila A., Regis M., Kraus S. Predictors of COVID-19 voluntary compliance behaviors: An international investigation. Global Transitions, 2020, vol. 2, pp. 76–82. https://doi.org/10.1016/j.glt.2020.06.003Khlobystova A.O., Abramov M.V., Tulupyev A.L. Soft estimates for social engineering attack propagation probabilities depending on interaction rates among instagram users // Studies in Computational Intelligence. 2020. V. 868. P. 272–277. https://doi.org/10.1007/978-3-030-32258-8_32Khlobystova A.O., Abramov M.V., Tulupyev A.L. Soft estimates for social engineering attack propagation probabilities depending on interaction rates among instagram users. Studies in Computational Intelligence, 2020, vol. 868, pp. 272–277. https://doi.org/10.1007/978-3-030-32258-8_32Piotrowski C., Sherry D., Keller J.W. Psychodiagnostic test usage: A survey of the society for personality assessment // Journal of Personality Assessment. 1985. V. 49. N 2. P. 115–119. https://doi.org/10.1207/s15327752jpa4902_1Piotrowski C., Sherry D., Keller J.W. Psychodiagnostic test usage: A survey of the society for personality assessment. Journal of Personality Assessment, 1985, vol. 49, no. 2, pp. 115–119. https://doi.org/10.1207/s15327752jpa4902_1Goldber L.R. An alternative “description of personality”: the big-five factor structure // Journal of Personality and Social Psychology. 1990. V. 59. N 6. P. 1216–1229. https://doi.org/10.1037/0022-3514.59.6.1216Goldber L.R. An alternative “description of personality”: the big-five factor structure. Journal of Personality and Social Psychology, 1990, vol. 59, no. 6, pp. 1216–1229. https://doi.org/10.1037/0022-3514.59.6.1216Schwartz S.H. A proposal for measuring value orientations across nations // Questionnaire Development Package of the European Social Survey. 2003. N 259(290). P. 261–319.Schwartz S.H. A proposal for measuring value orientations across nations. Questionnaire Development Package of the European Social Survey, 2003, no. 259(290), pp. 261–319.Cattell H.E.P., Mead A.D. The sixteen personality factor questionnaire (16PF) // The SAGE Handbook of Personality Theory and A s s e s s m e n t . V. 2 . 2 0 0 8 . P. 1 3 5 – 1 5 9 . https://doi.org/10.4135/9781849200479.n7Cattell H.E.P., Mead A.D. The sixteen personality factor questionnaire (16PF). The SAGE Handbook of Personality Theory and Assessment. V. 2, 2008, pp. 135–159. https://doi.org/10.4135/9781849200479.n7Plutchik R., Kellerman H., Conte H.R. A structural theory of ego defenses and emotions // Emotions, Personality, and Psychotherapy. Boston: Springer, 1979. P. 227–257. https://doi.org/10.1007/978-1-4613-2892-6_9Plutchik R., Kellerman H., Conte H.R. A structural theory of ego defenses and emotions. Emotions, Personality, and Psychotherapy. Boston, Springer, 1979, pp. 227–257. https://doi.org/10.1007/978-1-4613-2892-6_9Тулупьева Т.В., Тафинцева А.С., Тулупьев А.Л. Подход к анали зу отражения особенностей личности в цифровых следах // Вестник психотерапии. 2016. № 60(65). С. 124–137.Tulupyeva T.V., Tafintseva A.S., Tulupyev A.L. An approach to the analysis of personal traits reflection in digital traces. Bulletin of Psychotherapy, 2016, no. 60(65), pp. 124–137. (in Russian)Azucar D., Marengo D., Settanni M. Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis // Personality and Individual Differences. 2018. V. 124. P. 150–159. https://doi.org/10.1016/j.paid.2017.12.018Azucar D., Marengo D., Settanni M. Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis. Personality and Individual Differences, 2018, vol. 124, pp. 150–159. https://doi.org/10.1016/j.paid.2017.12.018Oliseenko V.D., Tulupyeva T.V. Neural network approach in the task of multi-label classification of user posts in online social networks // Proc. of the XXIV International Conference on Soft Computing and Measurements (SCM). 2021. P. 46–48. https://doi.org/10.1109/SCM52931.2021.9507148Oliseenko V.D., Tulupyeva T.V. Neural network approach in the task of multi-label classification of user posts in online social networks. Proc. of the XXIV International Conference on Soft Computing and Measurements (SCM), 2021, pp. 46–48. https://doi.org/10.1109/SCM52931.2021.9507148Oliseenko V.D., Eirich M., Tulupyev A.L., Tulupyeva T.V. BERT and ELMo in task of classifying social media users posts // Lecture Notes in Networks and Systems. 2023. V. 566. P. 475–486. https://doi.org/10.1007/978-3-031-19620-1_45Oliseenko V.D., Eirich M., Tulupyev A.L., Tulupyeva T.V. BERT and ELMo in task of classifying social media users posts. Lecture Notes in Networks and Systems, 2023, vol. 566, pp. 475–486. https://doi.org/10.1007/978-3-031-19620-1_45Tay L., Woo S.E., Hickman L., Saef R.M. Psychometric and validity issues in machine learning approaches to personality assessment: A focus on social media text mining // European Journal of Personality. 2020. V. 34. N 5. P. 826–844. https://doi.org/10.1002/per.2290Tay L., Woo S.E., Hickman L., Saef R.M. Psychometric and validity issues in machine learning approaches to personality assessment: A focus on social media text mining. European Journal of Personality, 2020, vol. 34, no. 5, pp. 826–844. https://doi.org/10.1002/per.2290Bleidorn W., Hopwood Ch.J. Using machine learning to advance personality assessment and theory // Personality and Social Psychology Review. 2019. V. 23. N 2. P. 190–203. https://doi.org/10.1177/1088868318772990Bleidorn W., Hopwood Ch.J. Using machine learning to advance personality assessment and theory. Personality and Social Psychology Review, 2019, vol. 23, no. 2, pp. 190–203. https://doi.org/10.1177/1088868318772990Kahn J.H., Tobin R.M., Massey A.E., Anderson J.A. Measuring emotional expression with the Linguistic Inquiry and Word Count // The American Journal of Psychology. 2007. V. 120. N 2. P. 263–286. https://doi.org/10.2307/20445398Kahn J.H., Tobin R.M., Massey A.E., Anderson J.A. Measuring emotional expression with the Linguistic Inquiry and Word Count. The American Journal of Psychology, 2007, vol. 120, no. 2, pp. 263– 286. https://doi.org/10.2307/20445398Hartmann J., Huppertz J., Schamp C., Heitmann M. Comparing automated text classification methods // International Journal ofResearch in Marketing. 2019. V. 36. N 1. P. 20–38. https://doi.org/10.1016/j.ijresmar.2018.09.009Hartmann J., Huppertz J., Schamp C., Heitmann M. Comparing automated text classification methods. International Journal of Research in Marketing, 2019, vol. 36, no. 1, pp. 20–38. https://doi.org/10.1016/j.ijresmar.2018.09.009Eichstaedt J.C., Kern M.L., Yaden D.B., Schwartz H.A., Giorgi S., Park G., Hagan C.A., Tobolsky V.A., Smith L.K., Buffone A., Iwry J., Seligman M.E.P., Ungar L.H. Closed and open-vocabulary approaches to text analysis: A review, quantitative comparison, and recommendations // Psychological Methods. 2021. V. 26. N 4. P. 398– 427. https://doi.org/10.1037/met0000349Eichstaedt J.C., Kern M.L., Yaden D.B., Schwartz H.A., Giorgi S., Park G., Hagan C.A., Tobolsky V.A., Smith L.K., Buffone A., Iwry J., Seligman M.E.P., Ungar L.H. Closed and open-vocabulary approaches to text analysis: A review, quantitative comparison, and recommendations. Psychological Methods, 2021, vol. 26, no. 4, pp. 398–427. https://doi.org/10.1037/met0000349Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // Proc. of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). V. 1. 2019. P. 4171–4186. https://doi.org/10.18653/v1/N19-1423Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). V. 1, 2019, pp. 4171–4186. https://doi.org/10.18653/v1/N19-1423Peters M.E., Neumann M., Iyyer M., Gardner M., Clark C., Lee K., Zettlemoyer L. Deep contextualized word representations // Proc. of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). V. 1. 2018. P. 2227–2237. https://doi.org/10.18653/v1/N18-1202Peters M.E., Neumann M., Iyyer M., Gardner M., Clark C., Lee K., Zettlemoyer L. Deep contextualized word representations. Proc. of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). V. 1, 2018, pp. 2227–2237. https://doi.org/10.18653/v1/N18-1202Brown T.B., Mann B., Ryder N., Subbiah M., Kaplan J.D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D., Wu J., Winter C., Hesse C., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner Ch., McCandlish S., Radford A., Sutskever I., Amodei D. Language models are few-shot learners // Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 2020.Brown T.B., Mann B., Ryder N., Subbiah M., Kaplan J.D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D., Wu J., Winter C., Hesse C., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner Ch., McCandlish S., Radford A., Sutskever I., Amodei D. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020.Sun J., Tian Z., Fu Y., Geng J., Liu C. Digital twins in human understanding: a deep learning-based method to recognize personality traits // International Journal of Computer Integrated Manufacturing. 2021. V. 34. N 7-8. P. 860–873. https://doi.org/10.1080/0951192X.2020.1757155Sun J., Tian Z., Fu Y., Geng J., Liu C. Digital twins in human understanding: a deep learning-based method to recognize personality traits. International Journal of Computer Integrated Manufacturing, 2021, vol. 34, no. 7-8, pp. 860–873. https://doi.org/10.1080/095119-2X.2020.1757155Wang Z., Wu C.-H., Li Q.-B., Yan B., Zheng K.-F. Encoding text information with graph convolutional networks for personality recognition // Applied Science. 2020. V. 10. N 12. P. 4081. https://doi.org/10.3390/app10124081Wang Z., Wu C.-H., Li Q.-B., Yan B., Zheng K.-F. Encoding text information with graph convolutional networks for personality recognition. Applied Science, 2020, vol. 10, no. 12, pp. 4081. https:// doi.org/10.3390/app10124081Cortes C., Vapnik V. Support-vector networks // Machine Learning. 1995. V. 20. N 3. P. 273–297. https://doi.org/10.1023/A:1022627411411Cortes C., Vapnik V. Support-vector networks. Machine Learning, 1 9 9 5 , v o l . 2 0 , n o . 3 , p p . 2 7 3 – 2 9 7 . https://doi.org/10.1023/A:1022627411411Breiman L. Random forests // Machine Learning. 2001. V. 45. N 1. P. 5–32. https://doi.org/10.1023/A:1010933404324Breiman L. Random forests. Machine Learning, 2001, vol. 45, no. 1, pp. 5–32. https://doi.org/10.1023/A:1010933404324Friedman N., Geiger D., Goldszmidt M. Bayesian network classifiers // Machine Learning. 1997. V. 29. N 2-3. P. 131–163. https://doi.org/10.1023/a:1007465528199Friedman N., Geiger D., Goldszmidt M. Bayesian network classifiers. Machine Learning, 1997, vol. 29, no. 2-3, pp. 131–163. https://doi.org/10.1023/a:1007465528199Grandini M., Bagli E., Visani G. Metrics for multi-class classification: an overview. 2020 [Электронный ресурс]. URL: https://arxiv.org/abs/2008.05756 (дата обращения: 01.09.2022).Grandini M., Bagli E., Visani G. Metrics for multi-class classification: an overview. 2020. Available at: https://arxiv.org/abs/2008.05756 (accessed: 01.09.2022).Refaeilzadeh P., Tang L., Liu H. Cross-Validation // Encyclopedia of Database Systems. Boston: Springer, 2009. P. 532–538. https://doi.org/10.1007/978-0-387-39940-9_565Refaeilzadeh P., Tang L., Liu H. Cross-Validation. Encyclopedia of Database Systems. Boston, Springer, 2009, pp. 532–538. https://doi.org/10.1007/978-0-387-39940-9_565Груздева А.С., Бессмертный И.А. Классификация коротких текстов с использованием волновой модели // Научно-технический вестник информационных технологий, механики и оптики. 2022. Т. 22. № 2. С. 287–293. https://doi.org/10.17586/2226-1494-2022-22-2-287-293Gruzdeva A.S., Bessmertny I.A. Classification of short texts using a wave model. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2022, vol. 22, no. 2, pp. 287– 293. (in Russian). https://doi.org/10.17586/2226-1494-2022-22-2-287-293 Authors Valerii D. Ol

The authors declare that there are no conflicts of interest present.