Go to NeSy 2025 Conference homepageTowards Explainable Depression Detection: A Neurosymbolic Approach to Uncover Social Media Signals with Generative AI
Keywords: Depression Detection, Neurosymbolic AI, Explainable AI, Social Media Analysis, Generative AI, Large Language Models, Prototype Learning, PHQ-9, Case-Based Reasoning, Neural Embeddings, Mental Health
TL;DR: We introduce ProtoDep, a neurosymbolic framework that uses clinical insights and generative AI to deliver transparent, explainable depression detection from social media data.
Track: Neurosymbolic Methods for Trustworthy and Interpretable AI
Abstract: Depression remains a pervasive mental health disorder that demands prompt diagnosis and intervention. Although social media data presents a promising avenue for early detection, traditional deep neural models are frequently critiqued for their lack of interpretability and susceptibility to bias. We introduce ProtoDep—a neurosymbolic framework that integrates clinically grounded categorizations (e.g., PHQ-9 symptoms) with large language model–assisted prototype learning. Unlike conventional black-box models, ProtoDep aligns individual tweets with symptom-level prototypes, offering interpretable explanations at three levels: (i) symptom-level insights that map user posts to recognized depressive patterns, (ii) case-based reasoning that compares users to representative prototype profiles, and (iii) transparent concept-level decisions, wherein classification at inference time is driven by the distances between the user profile and prototype user and symptom clusters, yielding clear, quantifiable explanations. By integrating symbolic mental health constructs with neural embeddings, ProtoDep achieves a mean F1-score of 94% across five benchmark datasets and establishes a foundation for interpretable depression screening pipelines with potential applicability in clinical settings.
Paper Type: Long Paper
Software: https://github.com/MahdaviNejad/ProtoDep
Submission Number: 44
Loading