Characterizing Network Structure of Anti-Trans Actors on TikTok
Maxyn Leitner, Rebecca Dorn, Fred Morstatter, Kristina Lerman
TL;DR
This work analyzes how anti-trans and pro-trans communities differ in TikTok network structures and how anti-trans content propagates on the platform. It introduces a Trans Sentiment Taxonomy and a RAG-enhanced classification pipeline built on LLaMA3 to label content as Pro-Trans, Anti-Trans, or Neutral, backed by expert annotators from the trans/nonbinary community. The study combines robust data collection from seed hashtags with network analysis of two interaction types (tag/reply and duet/stitch) to reveal that anti-trans actors are pervasive and interconnected with neutral users, while pro-trans clusters are smaller and more isolated. The findings offer actionable insights for moderation and underscore the need for nuanced, taxonomy-informed approaches to mitigate online harassment while supporting trans communities.
Abstract
The recent proliferation of short form video social media sites such as TikTok has been effectively utilized for increased visibility, communication, and community connection amongst trans/nonbinary creators online. However, these same platforms have also been exploited by right-wing actors targeting trans/nonbinary people, enabling such anti-trans actors to efficiently spread hate speech and propaganda. Given these divergent groups, what are the differences in network structure between anti-trans and pro-trans communities on TikTok, and to what extent do they amplify the effects of anti-trans content? In this paper, we collect a sample of TikTok videos containing pro and anti-trans content, and develop a taxonomy of trans related sentiment to enable the classification of content on TikTok, and ultimately analyze the reply network structures of pro-trans and anti-trans communities. In order to accomplish this, we worked with hired expert data annotators from the trans/nonbinary community in order to generate a sample of highly accurately labeled data. From this subset, we utilized a novel classification pipeline leveraging Retrieval-Augmented Generation (RAG) with annotated examples and taxonomy definitions to classify content into pro-trans, anti-trans, or neutral categories. We find that incorporating our taxonomy and its logics into our classification engine results in improved ability to differentiate trans related content, and that Results from network analysis indicate many interactions between posters of pro-trans and anti-trans content exist, further demonstrating targeting of trans individuals, and demonstrating the need for better content moderation tools