Sensing Societal Dynamics: Leveraging NLP-Based Psycholinguistic Features to Characterize Collective Action in China

In contemporary China, amid ongoing socioeconomic transformation, the emergence of collective action profoundly reflects and reshapes societal dynamics, underscoring the critical importance of in-depth research into this phenomenon. Previous studies have primarily leveraged media data or social media texts and behaviors to predict participation in collective action. Building on this line of research, the present study conducts an empirical analysis using textual data from the Weibo platform to explore linguistic patterns associated with different forms of collective action. Our findings indicate that goal-oriented “acquire” language is positively associated with the occurrence of disruptive and violent collective actions, whereas analytical “insight” language shows a negative association with violent actions. In addition, political and cultural terms show divergent associations across action types, remaining significant for conventional and disruptive collective action even after structural variables are controlled for. Moral discourse plays a divergent role depending on action intensity. Overall, the findings highlight the importance of motivational orientation and cognitive processing reflected in online language for understanding correlational patterns of collective action, and contribute to existing research on collective action in the digital era.