Climate and Weather: Inspecting Depression Detection via Emotion Recognition
This work addresses depression detection for mental health applications, but it is incremental as it builds on existing multimodal and transfer learning approaches.
The paper tackled automatic depression detection by transferring knowledge from emotion recognition models and fusing emotion with audio and text modalities, resulting in improved performance on the DAIC-WOZ dataset and increased training stability.
Automatic depression detection has attracted increasing amount of attention but remains a challenging task. Psychological research suggests that depressive mood is closely related with emotion expression and perception, which motivates the investigation of whether knowledge of emotion recognition can be transferred for depression detection. This paper uses pretrained features extracted from the emotion recognition model for depression detection, further fuses emotion modality with audio and text to form multimodal depression detection. The proposed emotion transfer improves depression detection performance on DAIC-WOZ as well as increases the training stability. The analysis of how the emotion expressed by depressed individuals is further perceived provides clues for further understanding of the relationship between depression and emotion.