Jointly modeling news semantics and news intent as heterogeneous graphs, connected by dynamic alignment pseudo-nodes, improves fake news detection on four benchmarks versus state-of-the-art baselines.
In Companion Proceedings of The Web Conference 2018, pages 585–593
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
-
Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection
Jointly modeling news semantics and news intent as heterogeneous graphs, connected by dynamic alignment pseudo-nodes, improves fake news detection on four benchmarks versus state-of-the-art baselines.