The relationship between linguistic expression in blog content and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study

• DOI: 10.1371/journal.pone.0251787
• Publication Date: 2021-05-19T17:40:12Z
• Authors: Bridianne O’Dea; Tjeerd W. Boonstra; Mark E. Larsen; Thin Nguyen; Svetha Venkatesh; Helen Christensen
• Keywords: Depression; Expression (computer science); Content (measure theory); Longitudinal Study

Data generated within social media platforms may present a new way to identify individuals who are experiencing mental illness. This study aimed investigate the associations between linguistic features in individuals’ blog data and their symptoms of depression, generalised anxiety, suicidal ideation. Individuals blogged were invited participate longitudinal which they completed fortnightly symptom scales for depression anxiety (PHQ-9, GAD-7) period 36 weeks. Blog published same was also collected, analysed using LIWC tool. Bivariate multivariate analyses performed correlations subjects. Multivariate regression models used predict changes A total 153 participants consented study. The final sample consisted 38 required number during period. Between-subject analysis revealed that “tentativeness” “non-fluencies” significantly correlated with but not thoughts. Within-subject showed no robust symptoms. findings provide evidence relationship some health; however, limited by missing other important considerations. suggest observed at group level generalise to, or be useful for, detecting individual change over time.