Skip to Main content Skip to Navigation
New interface
Conference papers

Multi-Task Learning for Depression Detection in Dialogs

Chuyuan Li 1 Chloé Braud 2, 3 Maxime Amblard 1 
1 SEMAGRAMME - Semantic Analysis of Natural Language
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
IRIT - Institut de recherche en informatique de Toulouse
Abstract : Depression is a serious mental illness that impacts the way people communicate, especially through their emotions, and, allegedly, the way they interact with others. This work examines depression signals in dialogs, a less studied setting that suffers from data sparsity. We hypothesize that depression and emotion can inform each other, and we propose to explore the influence of dialog structure through topic and dialog act prediction. We investigate a Multi-Task Learning (MTL) approach, where all tasks mentioned above are learned jointly with dialog-tailored hierarchical modeling. We experiment on the DAIC and DailyDialog corpora-both contain dialogs in English-and show important improvements over state-ofthe-art on depression detection (at best 70.6% F 1), which demonstrates the correlation of depression with emotion and dialog organization and the power of MTL to leverage information from different sources.
Complete list of metadata
Contributor : Maxime Amblard Connect in order to contact the contributor
Submitted on : Wednesday, July 20, 2022 - 10:36:19 AM
Last modification on : Thursday, August 25, 2022 - 3:48:28 AM


Files produced by the author(s)



Chuyuan Li, Chloé Braud, Maxime Amblard. Multi-Task Learning for Depression Detection in Dialogs. 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022), Sep 2022, Edinbourg, United Kingdom. pp.1-8, ⟨10.48550/arXiv.2208.10250⟩. ⟨hal-03724305⟩



Record views


Files downloads