Search papers, labs, and topics across Lattice.
This paper audits TikTok's mental health recommendations using 30 fresh accounts and LLM-guided agents to simulate different user intents (help-seeking vs. distress expression) and interaction strategies. The study found that user engagement with mental health content rapidly saturates feeds, while avoidance only modestly reduces exposure. Although help-initiated searches yield more supportive content, potentially harmful content, including suicide/self-harm related videos, persists, indicating limited sensitivity to user intent.
TikTok's algorithm floods users with mental health content regardless of whether they're seeking help or expressing distress, and even actively avoids harmful content.
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.
