Home >

news Help

Publication Information


Title
Japanese:ウェブ面接データを用いたうつ病の検出 
English:Detection of Depression Using Web-Interview Data 
Author
Japanese: Lam Cheuk Hee, Nah Nathania, 篠田 浩一, 北沢 桃子, 貝瀬 有里子, 高木 俊輔, 杉原 玄一, 岸本 泰士郎.  
English: Cheuk Hee Lam, Nathania Nah, Koichi Shinoda, Momoko Kitazawa, Yuriko Kaise, Shunsuke Takagi, Genichi Sugihara, Taishiro Kishimoto.  
Language English 
Journal/Book name
Japanese:電子情報通信学会技術研究報告 
English:IEICE Technical Report 
Volume, Number, Page vol. 124    no. 23    pp. 36-40
Published date May 8, 2024 
Publisher
Japanese:一般社団法人 電子情報通信学会 
English:The Institute of Electronics, Information and Communication Engineers (IEICE), Japan 
Conference name
Japanese:パターン認識・メディア理解研究会 (PRMU) 
English: 
Conference site
Japanese:東京都 
English: 
File
Official URL https://ken.ieice.org/ken/program/index.php?tgs_regid=aa725e3e7ec07887bababe264007abdede23a31140694fb0d0da9f5ecb36924d&tgid=IEICE-PRMU
https://ken.ieice.org/ken/paper/202405162cDd/
 
Abstract This paper presents a method for integrating speech, text, and video modalities for multimodal depression detection. Our work leverages shorter utterances to enhance depression detection accuracy, rather than relying on traditional long-term approaches. We introduce the COI-NEXT dataset, comprising authentic clinical interviews conducted through Zoom. Our experiments show that video modalities, particularly when using shorter utterances, lead to improved accuracy for depression detection in patients. Despite limitations due to data scarcity, this work offers valuable insights into multimodal depression detection, emphasizing the significance of multimodal integration in mental health research.

©2007 Institute of Science Tokyo All rights reserved.