Research Area:  Machine Learning
Major depressive disorder is a common mental disorder that affects almost 7% of the adult U.S. population. The 2017 Audio/Visual Emotion Challenge (AVEC) asks participants to build a model to predict depression levels based on the audio, video, and text of an interview ranging between 7-33 minutes. Since averaging features over the entire interview will lose most temporal information, how to discover, capture, and preserve useful temporal details for such a long interview are significant challenges. Therefore, we propose a novel topic modeling based approach to perform context-aware analysis of the recording. Our experiments show that the proposed approach outperforms context-unaware methods and the challenge baselines for all metrics.
Audio/Visual Emotion Challenge (AVEC)
Author(s) Name:  Yuan Gong , Christian Poellabauer
Conferrence name:  AVEC -17: Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge
Publisher name:  ACM
Paper Link:   https://dl.acm.org/doi/abs/10.1145/3133944.3133945