Personality driven method improves depression detection on social media
PAT: A Personality-Driven Augmentation and Transfer Learning Framework for Depression Detection on Social Media
Computation and Language
Summary
Detecting depression early through social media posts can help people get support sooner. Existing methods sometimes get confused by common wording and miss subtle signs in individual posts. The researchers developed a new way called PAT that uses personality theories to create better training data and learns detailed clues in each post. Their approach filters out irrelevant posts and improves identifying depression signs, also showing clear explanations for why posts indicate depression. This can help provide more reliable information for mental health professionals.
What this means in practice
- •For social media platform developers: Integrate the personality-driven filtering and detection method to improve accuracy of automated depression signals from user posts.
- •For mental health technology providers: Develop tools that trace individual user posts for depressive symptoms with interpretable insights supporting early intervention.$Commercial implications: Enables commercial mental health platforms to offer more precise and explainable depression monitoring services.
Authors
Shengwu Zheng, Yuzhe Ding, Xiaohui Liang, Fei Li, Chong Teng, Donghong Ji
Abstract
Depression is a prevalent mental disorder that affects millions worldwide, with early detection crucial for effective intervention. While exist?ing methods have achieved promising results in automated depression detection, they face two key limitations: (1) noise in post screening: symptom-based semantic screening is easily misled by superficial lexical patterns, thereby introducing false-positive posts; (2) weak op?timization of the post encoder: relying solely on coarse user-level supervision signals pre?vents models from capturing depressive cues within individual posts. To address these limita?tions, we propose PAT, a Personality-driven Augmentation and Transfer learning frame?work. In the first phase, PAT optimizes a post?level encoder via a fine-grained contrastive learning objective, utilizing LLM-based data augmentation driven by classic personality the?ories to alleviate data scarcity. In the second phase, the trained post-level scorer is deployed for high-quality post filtering, while its en?coder parameters are seamlessly transferred for user-level tasks. Extensive experiments demon?strate that PAT significantly outperforms exist?ing methods. Furthermore, PAT delivers multi?granular interpretability by tracing post-level mental-state trajectories and highlighting key symptoms, thereby offering reliable diagnostic evidence for clinical practice.