short form video social media sites

Maxyn Leitner (fae/faer) is a PhD student in USC ISI’s AI Division.  Faer research interests are computational social science, social network analysis, and AI bias/hate speech detection-namely how the spread of anti-trans sentiment on social media affects the network structures of trans and anti-trans communities on those platforms.  Fae pursues this by 1. proposing taxonomies of anti and pro-trans sentiment on social media grounded in queer theoretic and transfeminist literature 2. developing more effective AI classifiers based on these taxonomies and 3. utilizing said AI classifiers to reveal network patterns in online communities

Talk Description:

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? 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.  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

Join Zoom Meeting
Meeting ID: 633 3359 1885 / Passcode: 62801832