A Linguistically-Informed Fusion Approach for Multimodal Depression Detection

Michelle Morales, Stefan Scherer, Rivka Levitan


Abstract
Automated depression detection is inherently a multimodal problem. Therefore, it is critical that researchers investigate fusion techniques for multimodal design. This paper presents the first-ever comprehensive study of fusion techniques for depression detection. In addition, we present novel linguistically-motivated fusion techniques, which we find outperform existing approaches.
Anthology ID:
W18-0602
Volume:
Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic
Month:
June
Year:
2018
Address:
New Orleans, LA
Editors:
Kate Loveys, Kate Niederhoffer, Emily Prud’hommeaux, Rebecca Resnik, Philip Resnik
Venue:
CLPsych
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13–24
Language:
URL:
https://aclanthology.org/W18-0602
DOI:
10.18653/v1/W18-0602
Bibkey:
Cite (ACL):
Michelle Morales, Stefan Scherer, and Rivka Levitan. 2018. A Linguistically-Informed Fusion Approach for Multimodal Depression Detection. In Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic, pages 13–24, New Orleans, LA. Association for Computational Linguistics.
Cite (Informal):
A Linguistically-Informed Fusion Approach for Multimodal Depression Detection (Morales et al., CLPsych 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-0602.pdf