Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break
Napassorn Litchiowong

TL;DR
This paper models affective meaning divergence in conversations, revealing a critical transition point where communication breakdowns become abrupt, supported by empirical analysis of real dialogue data.
Contribution
It introduces a formal framework for affective divergence, combining game theory and speech-act theory, and identifies early warning signals of conversational collapse.
Findings
Derailing conversations show critical slowing down across multiple affective and dialog-act measures.
Affective meaning divergence variance peaks at the bifurcation point, serving as a theoretical indicator.
Toxicity and sentiment are less effective than AMD in signaling conversation breakdowns.
Abstract
One partner says "Fine" meaning "resolution"; the other hears "surrender." The word is shared; the affective uptake is not. We formalize this as affective meaning divergence (AMD), the total-variation distance between interlocutors' anchor-conditioned affect distributions. Building on speech-act theory, common-ground accumulation, and entropy-regularized game theory, we derive a logit best-response map whose dynamics undergo a saddle-node bifurcation: when , a monotone increase in AMD-driven load produces an abrupt, hysteretic collapse of repair coordination. On Conversations Gone Awry (CGA-Wiki; ), derailing conversations exhibit critical-slowing-down (CSD) signatures across multiple levels: lexical divergence variance (, ), AMD variance (, ), and dialog-act repair variance (, ), all significant…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
