Get Started
Home
Topics
Search
Library
Research questionHow can models predict and attribute sentiment shifts in branching rumor conversations to earlier discourse moves?A reply may respond to its parent, a distant ancestor, or several discourse moves such as correction, evidence, or attack. This structure makes it difficult to distinguish sentiment correlation from the earlier message that plausibly drove a change.
AI
Machine Learning
Natural Language Processing
Reasoning
Latest papersRecent research connected to this question, newest first.C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation TreesThe source studies public rumor conversation datasets with post-level sentiment, parent-child shift, discourse-move, and causal-source annotations. Evidence covers event-level generalization, ancestor attribution, and counterfactual analysis, including comparisons with text-only, graph-based, temporal, and prompted language-model baselines.research paper · Sep 2, 2026
Related questions
Can language models infer others’ mental states as social interactions evolve under unreliable information?How can multimodal models reason about fine-grained interpersonal relationships from conversational and visual cues?How can LLMs propagate local conversational revisions across dependent artifact components without excessive test-time computation?How can we quantify and reduce divergent, nonsensical reasoning in large language models?