Development of a Sentiment Analysis Tool to Identify Possible Signs of Depressive Behavior on the Twitter Social Network
DOI:
https://doi.org/10.5753/reic.2024.3430Keywords:
Twitter, Depression, Data mining, Supervised machine learning, COVID-19 Prepandemic, COVID-19 PandemicAbstract
Research on computerized models for identifying mental health issues in social media users has grown since the 2000s, mainly in English. Choudhury et al. and Coppersmith et al. proposed a method to detect depressive behavior using key attributes from Twitter posts, such as tweet quantity, personal pronouns, depressive terms, emotional tone, posting time, mentions of antidepressants, and follower responses. However, these posts are from before 2014 and don’t represent current Twitter user behavior, which now includes oriental characters, emojis, links, media (photos, videos, and gifs), and likes. Two databases of Portuguese tweets were created, covering pre-pandemic (01/01/2018 to 31/12/2019) and pandemic periods (01/01/2020 to 31/12/2021), divided into two categories: ”depression” and ”control, ”representing users with and without depression. These databases were used to assess the impact of the new attributes and develop a model for detecting depressive behavior through sentiment analysis of Portuguese tweets.
Downloads
References
AlSagri, H. S. and Ykhlef, M. (2020). Machine Learning-based Approach for Depression Detection in Twitter Using Content and Activity Features. IEICE Transactions on Information and Systems, E103.D(8):1825–1832. arXiv:2003.04763 [cs, stat].
Bollen, J., Pepe, A., and Mao, H. (2011). Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena. arXiv:0911.1583 [cs]. arXiv: 0911.1583.
Britto, L. and Pacífico, L. (2019). Analise de Sentimentos para Revisões de Aplicativos Mobile em Português Brasileiro. In Anais do Encontro Nacional de Inteligencia Artificial e Computacional (ENIAC), pages 1080–1090. SBC. ISSN: 2763-9061.
Coppersmith, G., Dredze, M., and Harman, C. (2014). Quantifying Mental Health Signals in Twitter. In Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, pages 51–60, Baltimore, Maryland, USA. Association for Computational Linguistics.
Corbanezi, E. (2018). Transtornos Depressivos e Capitalismo Contemporaneo. Caderno CRH, 31:335–353. Publisher: Universidade Federal da Bahia - Faculdade de Filosofia e Ciências Humanas - Centro de Recursos Humanos.
De Choudhury, M., Gamon, M., Counts, S., and Horvitz, E. (2013). Predicting Depression via Social Media. In Kiciman, E., Ellison, N. B., Hogan, B., Resnick, P., and Soboroff, I., editors, Proceedings of the Seventh International Conference on Weblogs and Social Media, ICWSM 2013, Cambridge, Massachusetts, USA, July 8-11, 2013. The AAAI Press.
Hassan, N. Y., Gomaa, W. H., Khoriba, G. A., and Haggag, M. H. (2020). Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques. International Journal of Intelligent Engineering & Systems, 13(1). JustAnotherArchivist (2022). Snscrape. original-date: 2018-09-09T20:16:31Z.
Kristensen, C. H., Gomes, C. F. d. A., Justo, A. R., and Vieira, K. (2011). Normas brasileiras para o Affective Norms for English Words. Trends in Psychiatry and Psychotherapy, 33:135–146. Publisher: Associação de Psiquiatria do Rio Grande do Sul.
Mendes, A. R., Passador, R. V. P., and Caseli, H. M. (2021). Identificando sintomas de depressão em postagens do Twitter em português do Brasil. In Anais do Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana (STIL), pages 162–171. SBC.
Mukaka, M. (2012). A guide to appropriate use of Correlation coefficient in medical research. Malawi Medical Journal : The Journal of Medical Association of Malawi, 24(3):69–71.
Park, M., Cha, C., and Cha, M. (2012). Depressive moods of users portrayed in Twitter. Proceedings of the 18th ACM International Conference on Knowledge Discovery and Data Mining, SIGKDD 2012, pages 1–8.
Rude, S., Gortner, E.-M., and Pennebaker, J. (2004). Language use of depressed and depression-vulnerable college students. Cognition and Emotion, 18(8):1121–1133. Publisher: Routledge eprint: https://doi.org/10.1080/02699930441000030.
Schroer, C., Kruse, F., and G ¨ omez, J. M. (2021). A Systematic Literature Review on Applying CRISP-DM Process Model. Procedia Computer Science, 181:526–534.
Stephen, J. J. and P, P. (2019). Detecting the magnitude of depression in Twitter users using sentiment analysis. International Journal of Electrical and Computer Engineering (IJECE), 9(4):3247–3255. Number: 4.
von Sperling, O. (2019). UnB Sense : a web application to probe for signs of depression from user profiles on social media. Accepted: 2021-02-01T16:59:26Z.
von Sperling, O. and Ladeira, M. (2019). Mining Twitter Data for Signs of Depression in Brazil. In Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe), pages 25–32. SBC. ISSN: 2763-8944.
Williams, K. L. and Galliher, R. V. (2006). Predicting Depression and Self–Esteem from Social Connectedness, Support, and Competence. Journal of Social and Clinical Psychology, 25(8):855–874. Publisher: Guilford Publications Inc.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Luan Mendes Gonçalves Freitas, Marcelo Ladeira, Marcos Fagundes Caetano
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
