Title: Narratives of Collective Action in YouTube's Discourse on Veganism

Abstract: Narratives can be powerful tools for inspiring action on pressing societal issues such as climate change. While social science theories offer frameworks for understanding the narratives that arise within collective movements, these are rarely applied to the vast data available from social media platforms, which play a significant role in shaping public opinion and mobilizing collective action. This gap in the empirical evaluation of online narratives limits our understanding of their relationship with public response. In this study, we focus on plant-based diets as a form of pro-environmental action and employ natural language processing to operationalize a theoretical framework of moral narratives specific to the vegan movement. We apply this framework to narratives found in YouTube videos promoting environmental initiatives such as Veganuary, Meatless March, and No Meat May. Our analysis reveals that several narrative types, as defined by the theory, are empirically present in the data. To identify narratives with the potential to elicit positive public engagement, we used text processing to estimate the proportion of comments supporting collective action across narrative types. Video narratives advocating social fight, whether through protest or through efforts to convert others to the cause, are associated with a stronger sense of collective action in the respective comments. These narrative types also demonstrate increased semantic coherence and alignment between the message and public response, markers typically associated with successful collective action. Our work offers new insights into the complex factors that influence the emergence of collective action, thereby informing the development of effective communication strategies within social movements.