JMIR Publications

ABSTRACT

Depression, a prevalent mental health condition, significantly impacts an individual’s thoughts, emotions, behaviours, and moods, affecting millions globally. Traditional approaches to detecting and treating depression rely on questionnaires and personal interviews, which can be time-consuming and potentially inefficient. Since social media has permanently shifted the pattern of our daily communications, social media postings can offer new perspectives in understanding mental illness in individuals since they provide an unbiased exploration of language usage and behavioural patterns of individuals. In our study, we propose a methodological language framework that integrates psychological patterns and states, contextual information, and the impact of social interactions leveraging Natural Language Processing (NLP) and Machine Learning (ML) techniques to improve intelligent decision-making in mental health. With accurate and effective detection of depression at the user level. We first extract language patterns that facilitate understanding contextual and psychological factors, such as affective patterns and personality traits linked with depression. Then, we extract social interaction influence features. The resultant social interaction influence that users have within their online social group is derived based on users’ emotions, psychological states, and context of communication extracted from status updates and the social network structure. This framework has practical ap- plications, including accelerating hospital diagnosis, improving prediction accuracy, providing timely referrals, and offering actionable insights for early interventions in mental health treatment plans.