What Are the Characteristics of User Texts and Behaviors in Chinese Depression Posts?

Abstract

Social media platforms provide unique insights into mental health issues, but a large number of related studies have focused on English text information. The purpose of this paper is to identify the posting content and posting behaviors of users with depression on Chinese social media. These clues may suggest signs of depression. We created two data sets consisting of 130 users with diagnosed depression and 320 other users that were randomly selected. By comparing and analyzing the two data sets, we can observe more closely how users reveal their signs of depression on Chinese social platforms. The results show that the distribution of some Chinese speech users with depression is significantly different from that of other users. Emotional sadness, fear and disgust are more common in the depression class. For personal pronouns, negative words and interrogative words, there are also great differences between the two data sets. Using topic modeling, we found that patients mainly discussed seven topics: negative emotion fluctuation, disease treatment and somatic responses, sleep disorders, sense of worthlessness, suicidal extreme behavior, seeking emotional support and interpersonal communication. The depression class post negative polarity posts much more frequently than other users. The frequency and characteristics of posts also reveal certain characteristics, such as sleep problems and reduced self-disclosure. In this study, we used Chinese microblog data to conduct a detailed analysis of the users showing depression signs, which helps to identify more patients with depression. At the same time, the study can provide a further theoretical basis for cross-cultural research of different language groups in the field of psychology.

Detecting depression of Chinese microblog users via text analysis: Combining Linguistic Inquiry Word Count (LIWC) with culture and suicide related lexicons

“…Firstly, different from most of the past studies ( 52 – 54 ), first person singular pronouns did not serve an important role in the model. Based on self-awareness theory, self-focused attention was one of the vulnerability factors for the onset and maintenance of depression ( 55 , 56 ).…”

Public Attitudes Toward Anxiety Disorder on Sina Weibo: Content Analysis (Preprint)

“…Text feature analysis Discover depression discrimination on social media Li et al [37] Text feature analysis Distinguish schizophrenia-related stigma from depression-related stigma Li et al [40] Qualitative content analysis Analyze the emotional polarity in tweets related to depression and schizophrenia Reavley and Pilkington [43] Qualitative content analysis Reveal the themes on tweets containing the tag #My depression looks like# in May 2016 Lachmar et al [44] Latent Dirichlet Allocation model (quantitative topic analysis) Detect content in social media containing self-harming thoughts and self-harming behaviors Franz et al [47] Latent Dirichlet Allocation model Reveal the topics talked about by depressed patients on the Sina Weibo platform Liu and Shi [28] Structural Topic Model and the network of words Analyze users' anxiety and worry concerns by analyzing data related to COVID-19 on Naver platform Jo et al [48] Ailment Topic Aspect Model Reveal the health-related topics in Twitter Paul and Dredze [50] Latent Dirichlet Allocation model and qualitative analysis Determine the optimal number of topics and their interpretation in depression forums Sik et al [51] Text feature analysis, Latent Dirichlet Allocation model and clustering algorithm Analyze health anxiety topics in midpandemic posts compared to those in prepandemic posts Low et al [52] Text feature analysis and Latent Dirichlet Allocation model Analyze public attitudes toward depression and the changes in these attitudes over time Yu et al [38]…”

“…A large number of studies in recent years have shown that social media data can be used to better understand, identify, and describe mental disorders [23,24] (eg, data from Facebook, Twitter, Instagram, Sina Weibo platforms). Individuals with mental disorders show changes in language and behavior, such as greater negative emotions and heightened self-attentive focus [25][26][27][28]. There is a high degree of similarity between patients with different forms of mental distress.…”

Public Attitudes Toward Anxiety Disorder on Sina Weibo: Content Analysis

“…A large number of studies in recent years have shown that social media data can be used to better understand, identify, and describe mental disorders [ 23 , 24 ] (eg, data from Facebook, Twitter, Instagram, Sina Weibo platforms). Individuals with mental disorders show changes in language and behavior, such as greater negative emotions and heightened self-attentive focus [ 25 - 28 ]. There is a high degree of similarity between patients with different forms of mental distress.…”

“…Franz et al [ 47 ] used the LDA model to detect content in social media containing self-harming thoughts and self-harming behaviors. Liu and Shi [ 28 ] used the LDA model to find that there were 7 main topics discussed by depressed patients on the Sina Weibo platform: negative emotion fluctuation, disease treatment and somatic responses, sleep disorders, sense of worthlessness, suicidal extreme behavior, seeking emotional support, and interpersonal communication. Jo et al [ 48 ] used a Structural Topic Model similar to the LDA model [ 49 ] to analyze users’ anxiety and worry concerns by analyzing data from 13,148 questions and 29,040 answers related to COVID-19 on Naver, a social networking platform in South Korea, and by using a structured topic model and a method of analyzing the network of words.…”