Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion

Aven Samareh, Yan Jin, Zhangyang Wang, Xiangyu Chang, Shuai Huang

AAAI 2018 pp. 8147-8148

doi:10.1609/AAAI.V32I1.12152 /aaai/2018/samareh2018aaai-predicting/

Abstract

We present our preliminary work to determine if patient's vocal acoustic, linguistic, and facial patterns could predict clinical ratings of depression severity, namely Patient Health Questionnaire depression scale (PHQ-8). We proposed a multi-modal fusion model that combines three different modalities: audio, video, and text features. By training over the AVEC2017 dataset, our proposed model outperforms each single-modality prediction model, and surpasses the dataset baseline with a nice margin.

PDF AAAI Semantic Scholar

Cite

Text

Samareh et al. "Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12152

Markdown

[Samareh et al. "Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/samareh2018aaai-predicting/) doi:10.1609/AAAI.V32I1.12152

BibTeX

@inproceedings{samareh2018aaai-predicting,
  title     = {{Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion}},
  author    = {Samareh, Aven and Jin, Yan and Wang, Zhangyang and Chang, Xiangyu and Huang, Shuai},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8147-8148},
  doi       = {10.1609/AAAI.V32I1.12152},
  url       = {https://mlanthology.org/aaai/2018/samareh2018aaai-predicting/}
}