Detecting and Tracking Depression Through Temporal Topic Modeling of Tweets: Insights from a 180-day Study

Overview

Journal Npj Ment Health Res

Publisher Springer Nature

Specialty Psychiatry

Date 2024 Dec 6

PMID 39643656

Authors

Ranganathan Chandrasekaran

Suhas Kotaki

Abhilash Hosaagrahaara Nagaraja

Affiliations

Soon will be listed here.

Abstract

Depression affects over 280 million people globally, yet many cases remain undiagnosed or untreated due to stigma and lack of awareness. Social media platforms like X (formerly Twitter) offer a way to monitor and analyze depression markers. This study analyzes Twitter data 90 days before and 90 days after a self-disclosed clinical diagnosis. We gathered 246,637 tweets from 229 diagnosed users. CorEx topic modeling identified seven themes: causes, physical symptoms, mental symptoms, swear words, treatment, coping/support mechanisms, and lifestyle, and conditional logistic regression assessed the odds of these themes occurring post-diagnosis. A control group of healthy users (284,772 tweets) was used to develop and evaluate machine learning classifiers-support vector machines, naive Bayes, and logistic regression-to distinguish between depressed and non-depressed users. Logistic regression and SVM performed best. These findings show the potential of Twitter data for tracking depression and changes in symptoms, coping mechanisms, and treatment use.

References

Rodriguez A, Holleran S, Mehl M . Reading between the lines: the lay assessment of subclinical depression from written self-descriptions. J Pers. 2010; 78(2):575-98. DOI: 10.1111/j.1467-6494.2010.00627.x. View

Oduntan A, Oyebode O, Beltran A, Fowles J, Steeves D, Orji R . "I Let Depression and Anxiety Drown Me…": Identifying Factors Associated With Resilience Based on Journaling Using Machine Learning and Thematic Analysis. IEEE J Biomed Health Inform. 2022; 26(7):3397-3408. DOI: 10.1109/JBHI.2022.3149862. View

Chandrasekaran R, Konaraddi K, Sharma S, Moustakas E . Text-Mining and Video Analytics of COVID-19 Narratives Shared by Patients on YouTube. J Med Syst. 2024; 48(1):21. DOI: 10.1007/s10916-024-02047-1. View

Lossio-Ventura J, Gonzales S, Morzan J, Alatrista-Salas H, Hernandez-Boussard T, Bian J . Evaluation of clustering and topic modeling methods over health-related tweets and emails. Artif Intell Med. 2021; 117:102096. PMC: 9040385. DOI: 10.1016/j.artmed.2021.102096. View

Hu M, Turner D, Generaal E, Bos D, Ikram M, Ikram M . Exercise interventions for the prevention of depression: a systematic review of meta-analyses. BMC Public Health. 2020; 20(1):1255. PMC: 7436997. DOI: 10.1186/s12889-020-09323-y. View

Pennebaker J, Seagal J . Forming a story: the health benefits of narrative. J Clin Psychol. 2000; 55(10):1243-54. DOI: 10.1002/(SICI)1097-4679(199910)55:10<1243::AID-JCLP6>3.0.CO;2-N. View

Seabrook E, Kern M, Fulcher B, Rickard N . Predicting Depression From Language-Based Emotion Dynamics: Longitudinal Analysis of Facebook and Twitter Status Updates. J Med Internet Res. 2018; 20(5):e168. PMC: 5964306. DOI: 10.2196/jmir.9267. View

Ricard B, Marsch L, Crosier B, Hassanpour S . Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram. J Med Internet Res. 2018; 20(12):e11817. PMC: 6302231. DOI: 10.2196/11817. View

Robbins M, Focella E, Kasle S, Lopez A, Weihs K, Mehl M . Naturalistically observed swearing, emotional support, and depressive symptoms in women coping with illness. Health Psychol. 2011; 30(6):789-92. PMC: 3193870. DOI: 10.1037/a0023431. View

10.

Kelley S, Mhaonaigh C, Burke L, Whelan R, Gillan C . Machine learning of language use on Twitter reveals weak and non-specific predictions. NPJ Digit Med. 2022; 5(1):35. PMC: 8956571. DOI: 10.1038/s41746-022-00576-y. View

11.

Cavazos-Rehg P, Krauss M, Sowles S, Connolly S, Rosas C, Bharadwaj M . A content analysis of depression-related Tweets. Comput Human Behav. 2015; 54:351-357. PMC: 4574287. DOI: 10.1016/j.chb.2015.08.023. View

12.

Shankar K, Chandrasekaran R, Jeripity Venkata P, Miketinas D . Investigating the Role of Nutrition in Enhancing Immunity During the COVID-19 Pandemic: Twitter Text-Mining Analysis. J Med Internet Res. 2023; 25:e47328. PMC: 10366666. DOI: 10.2196/47328. View

13.

Vaeth P, Ramisetty-Mikler S, Caetano R . Depression among couples in the United States in the context of intimate partner violence. J Interpers Violence. 2009; 25(5):771-90. PMC: 2909755. DOI: 10.1177/0886260509336957. View

14.

Barglow P . Self-disclosure in psychotherapy. Am J Psychother. 2005; 59(2):83-99. DOI: 10.1176/appi.psychotherapy.2005.59.2.83. View

15.

Birnbaum M, Ernala S, Rizvi A, De Choudhury M, Kane J . A Collaborative Approach to Identifying Social Media Markers of Schizophrenia by Employing Machine Learning and Clinical Appraisals. J Med Internet Res. 2017; 19(8):e289. PMC: 5575421. DOI: 10.2196/jmir.7956. View

16.

Zubaran C, Schumacher M, Roxo M, Foresti K . Screening tools for postpartum depression: validity and cultural dimensions. Afr J Psychiatry (Johannesbg). 2011; 13(5):357-65. DOI: 10.4314/ajpsy.v13i5.63101. View

17.

Meng Y, Speier W, Ong M, Arnold C . Bidirectional Representation Learning From Transformers Using Multimodal Electronic Health Record Data to Predict Depression. IEEE J Biomed Health Inform. 2021; 25(8):3121-3129. PMC: 8606118. DOI: 10.1109/JBHI.2021.3063721. View

18.

Sheng J, Liu S, Wang Y, Cui R, Zhang X . The Link between Depression and Chronic Pain: Neural Mechanisms in the Brain. Neural Plast. 2017; 2017:9724371. PMC: 5494581. DOI: 10.1155/2017/9724371. View

19.

Berry N, Lobban F, Belousov M, Emsley R, Nenadic G, Bucci S . #WhyWeTweetMH: Understanding Why People Use Twitter to Discuss Mental Health Problems. J Med Internet Res. 2017; 19(4):e107. PMC: 5399219. DOI: 10.2196/jmir.6173. View

20.

Mowery D, Smith H, Cheney T, Stoddard G, Coppersmith G, Bryan C . Understanding Depressive Symptoms and Psychosocial Stressors on Twitter: A Corpus-Based Study. J Med Internet Res. 2017; 19(2):e48. PMC: 5350450. DOI: 10.2196/jmir.6895. View