The computational turn in online mental health research: A systematic review

Abstract

Digital trace data and computational methods are increasingly being used by researchers to study mental health phenomena (i.e. psychopathology and well-being) in social media. Computer-assisted mental health research is not simply a continuation of previous studies, but rather raises ethical, conceptual and methodological issues that are critical to behavioural science but have not yet been systematically explored. Based on a systematic review of n = 147 studies, we reveal a multidisciplinary field of research that has grown immensely since 2010, spanning the humanities, social sciences, and engineering. We find that a substantial majority of studies in our sample lack a standardized form of ethical consideration, focus on specific constructs and have a rather narrow focus on specific social media platforms. Based on our findings, we discuss how computational elements have influenced mental health research, highlight academic gaps and suggest promising directions for future studies.

SMHD-GER: A Large-Scale Benchmark Dataset for Automatic Mental Health Detection from Social Media in German

“…The enormous societal impact of mental health conditions (MHC) requires prevention and intervention strategies that focus primarily on screening and early detection. The last decade has seen a surge in digital mental health research, an interdisciplinary line of research that brings together insights from computational linguistics, cognitive psychology and computational social sciences to understand the relationship between patterns of language use and mental health conditions (D'Alfonso, 2020; Schindler and Domahidi, 2022). Natural language processing, in particular, is increasingly recognized as having transformative potential to support healthcare professionals in the diagnosis and treatment of mental disorders and enable people to lead healthy lives (see Guntuku et al 2017;Thieme et al 2020;Chancellor and De Choudhury 2020;Zhang et al 2022 for recent overviews of this research).…”