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

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

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.