CT-LRP backpropagates relevance scores through a GNN and text embedding to produce class-specific token-level explanations for rumour detection, adding a contrastive step that filters tokens shared with other classes.
Real- time rumor debunking on twitter,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Contrastive Token-level Explanations for Graph-based Rumour Detection
CT-LRP backpropagates relevance scores through a GNN and text embedding to produce class-specific token-level explanations for rumour detection, adding a contrastive step that filters tokens shared with other classes.