Mental health, personality, and cross-addictions as predictors of social media addiction: a machine learning longitudinal study
Daniel Zarate, James Jarrad, Vasileios Stavropoulos, Connor Conkey-Morrison, Brian Hunt · 2026
Read Mental health, personality, and cross-addictions as predictors of social media addiction: a machine learning longitudinal study by Daniel Zarate, James Jarrad, Vasileios Stavropoulos, Connor Conkey-Morrison, Brian Hunt (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13312529.txt.
Description
Daniel Zarate and colleagues apply, in a 2026 longitudinal study, machine learning to forecast which social media users slide into problematic use. Earlier research on such compulsive engagement had produced inconsistent correlates, so the team let algorithms compete to predict risk over time from a wide pool of personal measures.
Data came from 276 adult users in Australia, the United Kingdom, New Zealand, and Canada, scored on the Bergen Social Media Addiction Scale. Random forests beat four rival models at predicting follow-up risk. The strongest signals were the person's own starting addiction score, anxiety including COVID-related anxiety, low agreeableness, and disengagement coping such as avoidance and escapism. The authors argue that early symptoms, persistent anxiety, and unhelpful coping keep problematic use going, and that interventions should target those levers.
Catalog record
| CREATOR | Daniel Zarate, James Jarrad, Vasileios Stavropoulos, Connor Conkey-Morrison, Brian Hunt |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46199 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |