User-level psychological stress detection from social media using deep neural network
Authors:
Open Access
- 3 November 2014
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 507-516
Abstract
It is of significant importance to detect and manage stress before it turns into severe problems. However, existing stress detection methods usually rely on psychological scales or physiological devices, making the detection complicated and costly. In this paper, we explore to automatically detect individuals' psychological stress via social media. Employing real online micro-blog data, we first investigate the correlations between users' stress and their tweeting content, social engagement and behavior patterns. Then we define two types of stress-related attributes: 1) low-level content attributes from a single tweet, including text, images and social interactions; 2) user-scope statistical attributes through their weekly micro-blog postings, leveraging information of tweeting time, tweeting types and linguistic styles. To combine content attributes with statistical attributes, we further design a convolutional neural network (CNN) with cross autoencoders to generate user-scope content attributes from low-level content attributes. Finally, we propose a deep neural network (DNN) model to incorporate the two types of user-scope attributes to detect users' psychological stress. We test the trained model on four different datasets from major micro-blog platforms including Sina Weibo, Tencent Weibo and Twitter. Experimental results show that the proposed model is effective and efficient on detecting psychological stress from micro-blog data. We believe our model would be useful in developing stress detection tools for mental health agencies and individuals.Keywords
Funding Information
- National Natural Science Foundation of China (61370023, 61373022)
- Ministry of Science and Technology of the People's Republic of China (2012CB316401, 2011CB302201)
- Microsoft Research (FY14-RES-SPONSOR-111)
This publication has 20 references indexed in Scilit:
- The Unfolded Protein Response: Integrating Stress Signals Through the Stress Sensor IRE1αPhysiological Reviews, 2011
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- The Psychological Meaning of Words: LIWC and Computerized Text Analysis MethodsJournal of Language and Social Psychology, 2009
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Learning multiple layers of representationTrends in Cognitive Sciences, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Detecting Stress During Real-World Driving Tasks Using Physiological SensorsIEEE Transactions on Intelligent Transportation Systems, 2005
- Stress and DepressionAnnual Review of Clinical Psychology, 2005
- Random Forest: A Classification and Regression Tool for Compound Classification and QSAR ModelingJournal of Chemical Information and Computer Sciences, 2003
- Stress and HealthAnnual Review of Public Health, 1984