Probabilistic Textual Time Series Depression Detection

ACL ARR 2025 July Submission1305 Authors

Abstract: Accurate and interpretable predictions of depression severity are essential for clinical decision support, yet existing models often lack uncertainty estimates and temporal modeling. We propose PTTSD, a Probabilistic Textual Time Series Depression Detection framework that predicts PHQ-8 scores from utterance-level clinical interviews while modeling uncertainty over time. PTTSD includes sequence-to-sequence and sequence-to-one variants, both combining bidirectional LSTMs, self-attention, and residual connections with Gaussian or Student’s-t output heads trained via negative log-likelihood. Evaluated on E-DAIC and DAIC-WOZ, PTTSD achieves state-of-the-art performance among text-only systems (e.g., MAE = 3.85 on E-DAIC, 3.55 on DAIC) and produces well-calibrated prediction intervals. Ablations confirm the value of attention and probabilistic modeling, while comparisons with MentalBERT establish generality. A three-part calibration analysis and qualitative case studies further highlight the interpretability and clinical relevance of uncertainty-aware forecasting.

Paper Type: Long

Research Area: Machine Learning for NLP

Research Area Keywords: multi-task learning, representation learning, structured prediction, transfer learning / domain adaptation, generalization

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: English

Submission Number: 1305