Seeking Help, Facing Harm: Auditing TikTok's Mental Health Recommendations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917413472174080 |
|---|---|
| author | Jamie, Pooriya Ghasemian, Amir Hosseinmardi, Homa |
| author_facet | Jamie, Pooriya Ghasemian, Amir Hosseinmardi, Homa |
| contents | Recommender systems on social media increasingly mediate how users encounter mental health content, yet it remains unclear whether they distinguish help-seeking from distress expression. We conduct a controlled 7-day audit of TikTok's "For You" page using 30 fresh accounts and LLM-guided agents that vary initial search framing (distress- vs. help-initiated) and interaction strategy (engaged, avoidant, passive). Across 8,727 recommended videos, interaction behavior dominates exposure outcomes: engagement rapidly saturates feeds with mental health content (~45% of daily recommendations), while avoidance and passive viewing reduce but do not eliminate exposure (~11-20%). Search framing mainly shifts composition rather than volume--help-initiated searches yield more potentially supportive material, yet potentially harmful content persists at low but non-zero levels, including content in the Suicide/Self-Harm category. These findings suggest limited sensitivity to user intent signals in TikTok's recommendations and motivate context-aware safeguards for sensitive topics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14832 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Seeking Help, Facing Harm: Auditing TikTok's Mental Health Recommendations Jamie, Pooriya Ghasemian, Amir Hosseinmardi, Homa Social and Information Networks Computers and Society K.4.2; H.3.5 Recommender systems on social media increasingly mediate how users encounter mental health content, yet it remains unclear whether they distinguish help-seeking from distress expression. We conduct a controlled 7-day audit of TikTok's "For You" page using 30 fresh accounts and LLM-guided agents that vary initial search framing (distress- vs. help-initiated) and interaction strategy (engaged, avoidant, passive). Across 8,727 recommended videos, interaction behavior dominates exposure outcomes: engagement rapidly saturates feeds with mental health content (~45% of daily recommendations), while avoidance and passive viewing reduce but do not eliminate exposure (~11-20%). Search framing mainly shifts composition rather than volume--help-initiated searches yield more potentially supportive material, yet potentially harmful content persists at low but non-zero levels, including content in the Suicide/Self-Harm category. These findings suggest limited sensitivity to user intent signals in TikTok's recommendations and motivate context-aware safeguards for sensitive topics. |
| title | Seeking Help, Facing Harm: Auditing TikTok's Mental Health Recommendations |
| topic | Social and Information Networks Computers and Society K.4.2; H.3.5 |
| url | https://arxiv.org/abs/2604.14832 |