EmoTrack uses LLM clinical signals plus frozen turn-level embeddings and compact cross-session memory to predict PHQ-8 scores, delivering a 13.5% MAE reduction on single-session DAIC-WOZ and competitive results on the new LongCounsel multi-session dataset.
Interpretable depression assessment using a large language model.PLOS Digital Health, 5(2):e0001205, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes
EmoTrack uses LLM clinical signals plus frozen turn-level embeddings and compact cross-session memory to predict PHQ-8 scores, delivering a 13.5% MAE reduction on single-session DAIC-WOZ and competitive results on the new LongCounsel multi-session dataset.