2 papers
cs.CL2026
Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features
Una Joh, Bei Yu
Topic models summarize large text corpora, but top-ranked words often provide only a limited representation of topic semantics. Sparse autoencoders (SAEs) offer a way to move beyon…
cs.SI2025
How Growing Toxicity Manifests: A Topic Trajectory Analysis of U.S. Immigration Discourse on Social Media
Una Joh, Yiqi Li, Jeff Hemsley
In the online public sphere, discussions about immigration often become increasingly fractious, marked by toxic language and polarization. Drawing on 4 million X posts over six mon…