EMDRC: Explainable Multimodal Depression Recognition for Clinical Interviews

NUSTM developed this multimodal dataset for explainable depression recognition in clinical interviews, with the most recent update occurring in January 2025. It provides data for affective computing research, specifically focusing on the intersection of mental health and machine learning interpretability.

Use Cases

• Training explainable models to identify depression markers in clinical interview transcripts.
• Fusing audio and visual features for multimodal affective computing tasks.
• Evaluating model interpretability for mental health diagnostics using clinical interview data.

Strengths

• Focuses on explainable AI (XAI) for clinical diagnostics
• Updated in January 2025
• Multimodal data integration for affective computing

Limitations

• Unknown record count and sample size
• Missing documentation on specific column names and data schemas
• No clear license for redistribution or commercial use

Provenance

Source

NUSTM (Nanjing University of Science and Technology)

Collection Method

Clinical interviews

Freshness

Last updated January 28, 2025.