PSYCH OpenIR  > 中国科学院行为科学重点实验室
Depressive Emotion Recognition Based on Behavioral Data
Yue Su1,2; Huijia Zheng1,3; Liu XQ(刘晓倩)1; Tingshao Zhu1
Conference NameHuman-Centered Computing (HCC 2018)
Source PublicationHCC 2018
Conference Date2018.12
Conference Place墨西哥


With the increase of pressure in people’s lives, depression has become one of the most common mental illness worldwide. The wide use of social media provides a new platform for depression recognition based on people’s behavioral data. This study utilizes the linguistical psychological characteristics of Weibo users to predict users’ depression level. The model adopts the Gaussian process regression algorithm, sets the PUK kernel as the kernel function, applies the forward-backward search method to select feature, and uses five-fold cross-validation to evaluate performance of the model. This study finally established a prediction model with a correlation coefficient of 0.5189, which achieved a medium correlation in the psychological definition, and provided a more accurate method for the auxiliary diagnosis of depression.

KeywordDiseases Learning systems Models Social networking
Indexed ByEI
Document Type会议论文
Affiliation1.Institute of Psychology, Chinese Academy of Sciences
2.Department of Psychology, University of Chinese Academy of Sciences
3.St. Mark’s School, Southborough
Recommended Citation
GB/T 7714
Yue Su,Huijia Zheng,Liu XQ,et al. Depressive Emotion Recognition Based on Behavioral Data[C],2019.
Files in This Item:
File Name/Size DocType Version Access License
2018_Book_HumanCente(48951KB)会议论文 限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yue Su]'s Articles
[Huijia Zheng]'s Articles
[Liu XQ(刘晓倩)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yue Su]'s Articles
[Huijia Zheng]'s Articles
[Liu XQ(刘晓倩)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yue Su]'s Articles
[Huijia Zheng]'s Articles
[Liu XQ(刘晓倩)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.