ERIC-FND

Code and appendix for External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection.

1. obtain the entity and entity description
2. combine the entity description with news texts to get the enhanced textual feature
3. do multimodal feature interactive enhancement
4. adaptively fuse the features and do the classification

For dataset, please see

https://github.com/MKLab-ITI/image-verification-corpus/tree/master

and

https://github.com/ICTMCG/DualEmotion

for more information.

If our code or models help your work, please cite our paper:

@inproceedings{Cao2025ERIC-FEND,
  author       = {Biwei Cao and
                  Qihang Wu and
                  Jiuxin Cao and
                  Bo Liu and
                  Jie Gui},
  editor       = {Toby Walsh and
                  Julie Shah and
                  Zico Kolter},
  title        = {External Reliable Information-enhanced Multimodal Contrastive Learning
                  for Fake News Detection},
  booktitle    = {AAAI-25, Sponsored by the Association for the Advancement of Artificial
                  Intelligence, February 25 - March 4, 2025, Philadelphia, PA, {USA}},
  pages        = {31--39},
  publisher    = {{AAAI} Press},
  year         = {2025},
  doi          = {10.1609/AAAI.V39I1.31977},
}