Modelling Thematic Structure in Clinical Dialogues for Interpretable Depression Detection
| Type of publication: | Conference paper |
| Citation: | Villatoro-Tello_TSD2026_2026 |
| Booktitle: | Text, Speech, and Dialogue. TSD 2026. Lecture Notes in Computer Science |
| Year: | 2026 |
| Month: | September |
| URL: | https://link.springer.com/chap... |
| DOI: | https://doi.org/10.1007/978-3-032-37249-9_47 |
| Abstract: | Detecting depression from clinical interviews requires models that capture discourse-level thematic structure rather than relying solely on lexical features. We propose Topic-GCN, a heterogeneous graph convolutional network that jointly encodes word, latent topic, and document nodes, enabling explicit modelling of topic–document associations for interview-level classification. The learned topic nodes surface interpretable symptom-relevant clusters whose class-conditional relevance can be mapped to established psycholinguistic categories. Experiments on the DAIC-WOZ and E-DAIC corpora show that Topic-GCN improves predictive performance over state-of-the-art methods while preserving interpretability. A post-hoc analysis using LIWC categories shows that the learned topic structure aligns with relevant symptom dimensions |
| Main Research Program: | AI for Everyone |
| Keywords: | Clinical Interviews, depression detection, digital mental health, Graph Neural Networks, Interpretability, topic modelling |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|