Agent-Based Splitting of Patient-Therapist Interviews for Depression Estimation

Abstract

There has been considerable research in the field of automated mental health analysis. Studies based on patient-therapist interviews usually treat the dyadic discourse as a sequence of sentences, thus ignoring individual sentence types (question or answer). To avoid this situation, we design a multi-view architecture that retains the symmetric discourse structure by dividing the transcripts into patient and therapist views. Experiments on the DAIC-WOZ dataset for depression level rating show performance improvements over baselines and state-of-the-art models.

Cite

Text

Agarwal et al. "Agent-Based Splitting of Patient-Therapist Interviews for Depression Estimation." NeurIPS 2022 Workshops: PAI4MH, 2022.

Markdown

[Agarwal et al. "Agent-Based Splitting of Patient-Therapist Interviews for Depression Estimation." NeurIPS 2022 Workshops: PAI4MH, 2022.](https://mlanthology.org/neuripsw/2022/agarwal2022neuripsw-agentbased/)

BibTeX

@inproceedings{agarwal2022neuripsw-agentbased,
  title     = {{Agent-Based Splitting of Patient-Therapist Interviews for Depression Estimation}},
  author    = {Agarwal, Navneet and Dias, Gaël and Dollfus, Sonia},
  booktitle = {NeurIPS 2022 Workshops: PAI4MH},
  year      = {2022},
  url       = {https://mlanthology.org/neuripsw/2022/agarwal2022neuripsw-agentbased/}
}