Characteristics for depression detection using Twitter data
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1319Keywords:
Data Mining, Pattern Recognition, Automated, DepressionAbstract
Objective: To identify the most relevant characteristics in detecting people with depression based on their Twitter posts. Method: Database creation, data preprocessing techniques, feature selection using hypothesis testing and AdaBoost classifier, and vocabulary size verification. Results: AdaBoost used 40 classifiers, 38 of which checked for the presence of specific words in the text, achieving an accuracy of 73%. It was found that the vocabulary of people with depression is smaller than that of people without depression. Conclusion: Checking for the presence of certain words in the tweets of depressed people is sufficient to achieve results close to those of more complex techniques. Additionally, the vocabulary of people with depression was shown to be smaller using a Shannon entropy-based approach.
References
Trifu RN, et al. Linguistic indicators of language in major depressive disorder (MDD). An evidence based research. J Evid Based Psychother. 2017;17(1).
Smirnova D, et al. Language patterns discriminate mild depression from normal sadness and euthymic state. Front Psychiatry. 2018;9:105.
Rude S, Gortner EM, Pennebaker J. Language use of depressed and depression-vulnerable college students. Cogn Emot. 2004;18(8):1121-1133.
Liu Y, et al. Predictors of depressive symptoms in college students: A systematic review and meta-analysis of cohort studies. J Affect Disord. 2019;244:196-208.
Santos WRD, de Oliveira RL, Paraboni I. SetembroBR: a social media corpus for depression and anxiety disorder prediction. Lang Res Evaluat. 2023.
Mann P, Paes A, Matsushima EH. See and read: detecting depression symptoms in higher education students using multimodal social media data. In: Proceedings of the International AAAI Conference on Web and Social Media. 2020. p. 440-451.
Alsagri HS, Ykhlef M. Machine learning-based approach for depression detection in Twitter using content and activity features. IEICE Trans Inf Syst. 2020;103(8):1825-1832.
Schapire RE. The boosting approach to machine learning: An overview. Nonlinear Estim Classif. 2003;149-171.
Domingos P. A few useful things to know about machine learning. Commun ACM. 2012;55(10):78-87.
Moreira LB, Namen AA. Sistema preditivo para a doença de Alzheimer na triagem clínica. J Health Inform. 2016;8(3).
Islam MR, et al. Depression detection from social network data using machine learning techniques. Health Inf Sci Syst. 2018;6:1-12.
Montalvao J, et al. On the representation of sparse stochastic matrices with state embedding [Pré-print]. Available at SSRN 4605637.
Armstrong RA. When to use the Bonferroni correction. Ophthalmic Physiol Opt. 2014;34(5):502-8.
Leis A, et al. Detecting signs of depression in tweets in Spanish: behavioral and linguistic analysis. J Med Internet Res. 2019;21(6):e14199.
Disner SG, Beevers CG, Haigh EA, Beck AT. Neural mechanisms of the cognitive model of depression. Nat Rev Neurosci. 2011;12(8):467-77.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
