Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews

Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews

Paper in proceedings (conference paper)

We propose a simple approach for weighting self- connecting edges in a Graph Convolutional Network (GCN) and show its impact on depression detection from transcribed clinical interviews. To this end, we use a GCN for model- ing non-consecutive and long-distance semantics to classify the transcriptions into depressed or control subjects. The proposed method aims to mitigate the limiting assumptions of locality and the equal importance of self-connections vs. edges to neighbor- ing nodes in GCNs, while preserving attractive features such as low computational cost, data agnostic, and interpretability capa- bilities. We perform an exhaustive evaluation in two benchmark datasets. Results show that our approach consistently outper- forms the vanilla GCN model as well as previously reported re- sults, achieving an F1=0.84% on both datasets. Finally, a qual- itative analysis illustrates the interpretability capabilities of the proposed approach and its alignment with previous findings in psychology.

We propose a simple approach for weighting self- connecting edges in a Graph Convolutional Network (GCN) and show its impact on depression detection from transcribed clinical interviews. To this end, we use a GCN for model- ing non-consecutive and long-distance semantics to classify the transcriptions into depressed or control subjects. The proposed method aims to mitigate the limiting assumptions of locality and the equal importance of self-connections vs. edges to neighbor- ing nodes in GCNs, while preserving attractive features such as low computational cost, data agnostic, and interpretability capa- bilities. We perform an exhaustive evaluation in two benchmark datasets. Results show that our approach consistently outper- forms the vanilla GCN model as well as previously reported re- sults, achieving an F1=0.84% on both datasets. Finally, a qual- itative analysis illustrates the interpretability capabilities of the proposed approach and its alignment with previous findings in psychology.

depression detection, graph neural networks, node weighted graphs, limited training data, interpretability.

depression detection, graph neural networks, node weighted graphs, limited training data, interpretability.

BURDISSO, S.; VILLATORO-TELLO, E.; MADIKERI, S.; MOTLÍČEK, P.

2024

20.08.2023

International Speech Communication Association

Dublin

Proceedings of the Annual Conference of International Speech Communication Association, INTERSPEECH

1990-9772

Proceedings of Interspeech

2023

8

French Republic

3617

3621

5

https://www.isca-archive.org/interspeech_2023/burdisso23_interspeech.pdf

burdisso23_interspeech