AI-Enhanced Mental Health Risk Analysis Using Social Media Data

Nallajonnala, Ramanaidu (2025) AI-Enhanced Mental Health Risk Analysis Using Social Media Data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (750kB) | Preview
Preview	PDF (Configuration Manual) Download (798kB) | Preview

Abstract

The paper presents an AI-powered system for mental health risk detection based on social media data, incorporating sentiment trajectories, temporal posting, and social engagement features. The task at hand was to conceptualize, implement, and compare different models—with logistic regression and Long Short-Term Memory (LSTM) on one side and transformer-based Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) on the other—to evaluate their performance in depressive cue detection. The data was derived from a labelled public Twitter corpus, pre-processed for linguistic as well as for the extraction of behavioural features, and evaluated on traditional classification metrics. Of all the models evaluated, Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) performed the best, affirming value in leveraging deep contextual embeddings. Feature interpretability was provided in terms of temporal features as well as engagement-based features, conforming to Responsible AI standards. The current paper attaches special significance to multi-modal modelling of behaviour for early identification of mental health risk and advocates for its use in real-time monitoring as well as ethical systems for digital intervention.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Uncontrolled Keywords:	Mental Health Detection; Social Media Analytics; Transformer Models; Sentiment Trajectory; DistilBERT; LSTM; Temporal Analysis; Behavioural AI; Classification Metrics; Explainable AI
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence R Medicine > RA Public aspects of medicine > RA790 Mental Health Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	26 Aug 2026 09:46
Last Modified:	26 Aug 2026 09:46
URI:	https://norma.ncirl.ie/id/eprint/9651

Actions (login required)

View Item