Detecting changes in attitudes toward depression on Chinese social media: A text analysis

Background & Aims: Depression is a common and sometimes severe form of mental illness, and public attitudes towards depression can impact the psychological and social functioning of depressed patients. The purpose of the present study was to investigate public attitudes toward depression and three-year trends in these attitudes using big data analysis of social media posts in China. Methods: A search of publically available Sina Weibo posts from January 2014 to July 2017 identified 20,129 hot posts with the keyword term “depression”. We first used a Chinese Linguistic Psychological Text Analysis System (TextMind) to analyze linguistic features of the posts. And, then we used topic models to conduct semantic content analysis to identify specific themes in Weibo users’ attitudes toward depression. Results: Linguistic features analysis showed a significant increase over time in the frequency of terms related to affect, positive emotion, anger, cognition (including the subcategory of insight), and conjunctions. Semantic content analysis identified five common themes: severe effects of depression, stigma, combating stigma, appeals for understanding, and providing support. There was a significant increase over time in references to social (as opposed to professional) support, and a significant decrease over time in references to the severe consequences of depression. Conclusions: Big data analysis of Weibo posts is likely to provide less biased information than other methods about the public\u27s attitudes toward depression. The results suggest that although there is ongoing stigma about depression, there is also an upward trend in mentions of social support for depressed persons. A supervised learning statistical model can be developed in future research to provide an even more precise analysis of specific attitudes