Explainable Depression Detection using Masked Hard Instance Mining
This addresses the need for more interpretable models in mental health diagnostics, though it is incremental as it builds on existing attention-based methods.
The paper tackled the problem of poor explainability in text-based depression detection by proposing Masked Hard Instance Mining (MHIM), which improved both prediction accuracy and explainability metrics on Thai and English datasets.
This paper addresses the critical need for improved explainability in text-based depression detection. While offering predictive outcomes, current solutions often overlook the understanding of model predictions which can hinder trust in the system. We propose the use of Masked Hard Instance Mining (MHIM) to enhance the explainability in the depression detection task. MHIM strategically masks attention weights within the model, compelling it to distribute attention across a wider range of salient features. We evaluate MHIM on two datasets representing distinct languages: Thai (Thai-Maywe) and English (DAIC-WOZ). Our results demonstrate that MHIM significantly improves performance in terms of both prediction accuracy and explainability metrics.