Uncovering Emotions: Using IoT as a Psychodiagnostics Tool

Abstract

The current study is situated within the intersection of mood-tracking algorithms and draws on expertise in machine learning. Within the mixed-method approach, 40 participants were interviewed using semi-structured interviews and measured against a standardized mental health scale to gauge their moods. The work derives detailed understanding about the complex dynamics between users and these algorithms, describing their role in affecting emotional well-being amidst pervasive digital monitoring. It focuses more on the trends of screen time and how this relates to emotional states. This research strived to bring about not only the psychological implications of merging such algorithms in our digital lives, but also their efficacy in the clinical diagnosis of mental health disorders. This shows that increased screen time is strongly related to a rising susceptibility to major depression disorder and anxiety disorder. This baseline result showed important differences in the level of depression and anxiety among different content engagement groups and thus implies the differential effect of content types on the mental health of users. The study represents the potential of emotional tracking algorithms in detecting mental health problems, underlining the critical intersection of digital engagement and psychological well-being within the context of IoT.