Thesis Proposal (Zihao He)

Committee members:
Kristina Lerman (Chair)
Emilio Ferrara
Jonathan May
Fred Morstatter
Marlon Twyman
 
Title: Exploring Polarization and Ideological Difference of Online Communities Through Language Models
 
Abstract: The proliferation of diverse information sources and social platform interactions has led to increased ideological polarization, presenting unique challenges in understanding and quantifying these divides. This thesis tackles the nuanced task of analyzing ideological polarization of  online communities through language models. First, I extract contextualized topic embeddings from a pretrained language model, focusing on identifying polarized topics within various information sources. Next, I use a generative language model to probe into the ideological dimensions within social media discourse, specifically examining Twitter conversations around key political figures; this approach uncovers the complexities within user interactions and the formation of opinion clusters. Finally, I investigate the alignment between the affective responses of large language models and human ideologies. 

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 131A

Audiences: Everyone Is Invited

Contact: CS Events

Event Link: https://usc.zoom.us/j/98773410609?pwd=SXQzekVMZjZ6dVhSdWJCRGlrVlFFZz09