Social media posts reveal depression severity with user focused analysis
Words Are the Voice of the Mind: Depression Severity Estimation from Social Traces via Mental-Guided Evidence Reasoning
Computation and Language
Summary
Estimating how severe someone's depression is usually needs personal interviews or questionnaires, which can be hard to get. The authors present a method that looks at a person’s past social media posts to understand their mental state better. Their system creates a personalized mental profile from these posts and finds specific evidence related to depression symptoms, then carefully reasons to estimate the severity of depression with clear explanations. This approach performs competitively and can work for other tasks based on similar rating scales.
What this means in practice
- •For mental health platform developers: Create tools that estimate user depression severity from social media content with personalized mental profiles and explainable evidence.$Commercial implications: Enables development of depression monitoring services that provide automated, interpretable assessments from social media data.
- •For social media content analysts: Enhance analysis of mental states by incorporating user-specific behavioral patterns and fine-grained evidence reasoning to improve depression-related insights.
Authors
Nada Xu, Xueqin Chen, Qiang Gao, Hongru Liang, Wenqiang Lei
Abstract
Depression severity estimation is crucial for mental health assessment and intervention, yet traditional approaches depend on clinical interviews or self-report questionnaires that require users' active participation. With the widespread use of online social media, users leave rich social traces that may reflect their mental states, motivating the task of social media-based depression severity estimation. Existing efforts have progressed from textual-feature-based classification to LLM-based questionnaire completion over standardized scale items, yet they still fall short in user-specific mental priors modeling, diversified semantic retrieval, and fine-grained reasoning over mental evidence. To address these limitations, we propose UMer, a user-specific mental evidence reasoning framework for social traces-based depression severity estimation. UMer first distills a user-specific mental prior from historical social traces to capture the user's psychological tendencies, behavioral patterns, and self-expression style. It then performs scale-guided multi-query retrieval to construct evidence memories from item-relevant posts. Finally, it conducts coarse-to-fine evidence-aware reasoning to distinguish direct and indirect evidence and predict item-level scores with interpretable rationales. Extensive experiments on real-world benchmarks demonstrate that UMer not only achieves competitive performance over existing baselines, but also provides evidence-grounded interpretability and generalizes to other scale-based tasks.