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

Abstract

IntroductionIn recent years, research has used psycholinguistic features in public discourse, networking behaviors on social media and profile information to train models for depression detection. However, the most widely adopted approach for the extraction of psycholinguistic features is to use the Linguistic Inquiry Word Count (LIWC) dictionary and various affective lexicons. Other features related to cultural factors and suicide risk have not been explored. Moreover, the use of social networking behavioral features and profile features would limit the generalizability of the model. Therefore, our study aimed at building a prediction model of depression for text-only social media data through a wider range of possible linguistic features related to depression, and illuminate the relationship between linguistic expression and depression.MethodsWe collected 789 users’ depression scores as well as their past posts on Weibo, and extracted a total of 117 lexical features via Simplified Chinese Linguistic Inquiry Word Count, Chinese Suicide Dictionary, Chinese Version of Moral Foundations Dictionary, Chinese Version of Moral Motivation Dictionary, and Chinese Individualism/Collectivism Dictionary.ResultsResults showed that all the dictionaries contributed to the prediction. The best performing model occurred with linear regression, with the Pearson correlation coefficient between predicted values and self-reported values was 0.33, the R-squared was 0.10, and the split-half reliability was 0.75.DiscussionThis study did not only develop a predictive model applicable to text-only social media data, but also demonstrated the importance taking cultural psychological factors and suicide related expressions into consideration in the calculation of word frequency. Our research provided a more comprehensive understanding of how lexicons related to cultural psychology and suicide risk were associated with depression, and could contribute to the recognition of depression.

Exploring Multidimensional Aspects of Hope Speech Computationally: A Psycholinguistic and Emotional Perspective

“…LIWC: The introduction of the LIWC model represented a significant leap forward in psychological research, elevating the strength, accessibility, and scientific integrity of language data analysis. The recent LIWC-22 (LIWC, 2024) explores over 100 textual dimensions rigorously validated by esteemed research institutions globally (Lyu et al, 2023). With over 20,000 scientific publications utilizing LIWC, it has become a highly esteemed and indispensable tool in the field of NLP (LIWC, 2024;Bojić, 2023).…”

Psycholinguistic and emotion analysis of cryptocurrency discourse on X platform

“…LIWC-22 examines over 100 textual dimensions, all of which have undergone validation by esteemed research institutions globally. With over 20,000 scientific publications utilizing LIWC, it has become a widely recognized and trusted tool in the field 62 giving way to novel approaches in analysis 63 , 64 . Although LIWC provides several benefits, it has its limitations.…”

Users’ Behavioral and Emotional Response to Toxicity in Twitter Conversations

“…For example, users might get more angry if they receive a toxic reply concerning their political views, or they might get sad if the toxicity is directed at their health-related decisions. Thus, a recent topic classification model (Antypas et al 2022) used in previous studies (Leiter et al 2024) was utilized to determine the main topic of the conversation by passing the text of the main tweet as the input. Note that this model has been fine-tuned for multi-label classification on 11,267 tweets yielding 19 discussion topics such as news & social concern, diaries & daily life, business & entrepreneurs, and others.…”

“…This tool analyzes text to provide insights into the person's emotions, social and cognitive processes, etc. It has been used for psychological analysis of users online (Lyu et al 2023) and it has shown a decent performance for detecting emotions in verbal expression (Kahn et al 2007). It treats each tweet individually and provides scores for each post in range 0−99, representing its relation to a specific attribute.…”