Cross-Domain Depression Detection via Harvesting Social Media
Tiancheng Shen ; Jia Jia ; Guangyao Shen ; Fuli Feng ; Xiangnan He ; Huanbo Luan ; Jie Tang ; Thanassis Tiropanis ; Tat-Seng Chua ; Wendy Hall
Tiancheng Shen
Jia Jia
Guangyao Shen
Thanassis Tiropanis
Wendy Hall
Citations
Altmetric:
Alternative Title
Abstract
Depression detection is a significant issue for human well-being. In previous studies, online detection has proven effective in Twitter, enabling proactive care for depressed users. Owing to cultural differences, replicating the method to other social media platforms, such as Chinese Weibo, however, might lead to poor performance because of insufficient available labeled (self-reported depression) data for model training. In this paper, we study an interesting but challenging problem of enhancing detection in a certain target domain (e.g. Weibo) with ample Twitter data as the source domain. We first systematically analyze the depression-related feature patterns across domains and summarize two major detection challenges, namely isomerism and divergency. We further propose a cross-domain Deep Neural Network model with Feature Adaptive Transformation & Combination strategy (DNN-FATC) that transfers the relevant information across heterogeneous domains. Experiments demonstrate improved performance compared to existing heterogeneous transfer methods or training directly in the target domain (over 3.4% improvement in F1), indicating the potential of our model to enable depression detection via social media for more countries with different cultural settings. © 2018 International Joint Conferences on Artificial Intelligence. All right reserved.
Keywords
Source Title
EMNLP 2018
Publisher
International Joint Conferences on Artificial Intelligence
Series/Report No.
Collections
Rights
Date
2018-10-27
DOI
10.24963/ijcai.2018/223
Type
Conference Paper