# Depression Symptoms and Relational Patterns in 187k ChatGPT Histories

arXiv: https://arxiv.org/abs/2607.05685 · HTML: https://mlsanity.com/paper/2607.05685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [The opportunities and risks of large language models in mental health](https://mlsanity.com/paper/2403.14814/) (2024)
- [Sycophantic AI makes human interaction feel more effortful and less satisfying over time](https://mlsanity.com/paper/2605.07912/) (2026)
- [The Social Sycophancy Scale: A psychometrically validated measure of sycophancy](https://mlsanity.com/paper/2603.15448/) (2026)
- [Exploring Socio-Cultural Challenges and Opportunities in Designing Mental Health Chatbots for Adolescents in India](https://mlsanity.com/paper/2503.08562/) (2025)
- [Bowling with ChatGPT: On the Evolving User Interactions with Conversational AI Systems](https://mlsanity.com/paper/2602.01114/) (2026)
- [Designing Mental-Health Chatbots for Indian Adolescents: Mixed-Methods Evidence, a Boundary-Object Lens, and a Design-Tensions Framework](https://mlsanity.com/paper/2511.07729/) (2025)

## Abstract (arXiv)

Large language models are increasingly used as private, always-available conversational systems, but little is known about how people with depressive symptoms use them. Building on CSCW work on disclosure and peer support, we examine ChatGPT as an emerging informal support infrastructure: private, persistent, responsive, and available outside ordinary hours. We analyze 187,093 ChatGPT conversations from 766 participants who completed the PHQ-8, comparing those below the moderate-symptom threshold (score of 10) with those at or above it. Higher-PHQ participants used ChatGPT more for mental-health, interpersonal, loneliness, self-focused, and support-seeking conversations, with pronounced late-night and recurring month-level patterns. Their language contained more first-person singular pronouns and absolutist terms. They more often engaged ChatGPT in high-disclosure contexts, but professional redirection was not higher. Language-based prediction was modest and insufficient for screening (AUROC 0.591). We argue these histories should not be treated as clinical screening data but as evidence LLMs are increasingly used as informal support infrastructure.