EmoTrack：面向文本抑郁严重度估计的临床语义建模方法

View PDF HTML (experimental)

Abstract:Text-based counseling is widely adopted across online mental health platforms, where automatically estimating depressive symptom severity from transcripts is vital for client safety and clinical monitoring. We therefore study prediction of the standard eight-item Patient Health Questionnaire (PHQ-8) total score directly from counseling sessions. Existing clinical-based methods obtain structured assessments through large language model inference but summarize away individual client turns. Training-based methods preserve turn semantics but must learn clinical structure from limited labels. Integrating these representations requires preserving clinical-feature identity and selecting evidence relevant to each symptom. We propose EmoTrack, which jointly encodes clinical-feature tokens and frozen client-turn embeddings, then uses PHQ-8 item queries to estimate total severity. Optional gated memory incorporates evidence from the preceding session. To support controlled evaluation in the multi-session setting, we introduce CounselArc, a synthetic counseling dataset with session-level PHQ-8 supervision for predicting current-session severity with optional prior-session context. Across real DAIC-WOZ interviews, transfer to E-DAIC, and three longitudinal datasets, EmoTrack achieves the lowest normalized aggregate error. It reduces DAIC-WOZ mean absolute error by 12.5% and aggregate error by approximately 8.6%, each relative to the strongest baseline for that measure.

Comments:	36 pages. Related LongCounsel-8 benchmark: arXiv:2609.03507
Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2605.22286 [cs.LG]
	(or arXiv:2605.22286v3 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2605.22286 arXiv-issued DOI via DataCite

Submission history

From: Jiayi Li [view email]
[v1] Thu, 21 May 2026 10:37:45 UTC (576 KB)
[v2] Tue, 8 Sep 2026 13:05:25 UTC (534 KB)
[v3] Wed, 4 Nov 2026 14:41:55 UTC (302 KB)