Linking Extreme Discourse to Structural Polarization in Signed Interaction Networks

ArXi:2605.12814v1 Announce Type: cross Polarization in online communities is often studied through either language or interaction structure, but the two views are rarely connected in a unified measurement pipeline. Prior work links them by building interaction graphs from human judgments of agreement and disagreement, leaving a gap between language as observed text and structure as an engineered representation of that text.