Summary of Enriching Gnns with Text Contextual Representations For Detecting Disinformation Campaigns on Social Media, by Bruno Croso Cunha Da Silva et al.
Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media
by Bruno Croso Cunha da Silva, Thomas Palmeira Ferraz, Roseli De Deus Lopes
First submitted to arxiv on: 24 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Disinformation on social media poses significant challenges that require robust detection systems. This paper addresses this gap by integrating Transformer-based textual features into Graph Neural Networks (GNNs) for fake news detection. By incorporating high-quality contextual text representations, the authors demonstrate a 33.8% relative improvement in Macro F1 over models without textual features and 9.3% over static text representations. The work also investigates the impact of different feature sources and noisy data augmentation. This methodology has the potential to open avenues for further research, and the code is publicly available. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Social media can spread false information quickly. To stop this from happening, we need better ways to detect fake news. One way to do this is by using special computer models that understand language. This paper shows how combining these language models with other techniques called Graph Neural Networks (GNNs) can help detect fake news more accurately. The researchers found that their method was 9.3% better than previous methods and they also discovered what happens when you add different types of data to the mix. They made their code public so others can use it too. |
Keywords
» Artificial intelligence » Data augmentation » Transformer
