English

Topic Modeling Based Multi-modal Depression Detection

Computation and Language 2018-03-29 v1 Information Retrieval Machine Learning Sound Audio and Speech Processing

Abstract

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.

Keywords

Cite

@article{arxiv.1803.10384,
  title  = {Topic Modeling Based Multi-modal Depression Detection},
  author = {Yuan Gong and Christian Poellabauer},
  journal= {arXiv preprint arXiv:1803.10384},
  year   = {2018}
}

Comments

Proceedings of the 7th Audio/Visual Emotion Challenge and Workshop (AVEC). (Official Depression Challenge Winner)

R2 v1 2026-06-23T01:07:09.216Z