Authors: Shaina Raza, Tahniat Khan, Drai Paulen-Patterson, Veronica Chatrath, Mizanur Rahman, Oluwanifemi Bamgbose

Published on: March 14, 2024

Impact Score: 8.4

Arxiv code: Arxiv:2403.09858

Summary

• What is new: Introduces FakeWatch, a framework with a hybrid approach combining traditional machine learning and language models to detect fake news related to elections.
• Why this is important: The rampant spread of fake news, especially during critical times like elections, undermines information integrity.
• What the research proposes: FakeWatch framework leveraging a novel dataset of North American election news alongside a model hub for classifying fake news.
• Results: State-of-the-art Language Models perform slightly better than traditional ML models, though the latter remains competitive in accuracy and efficiency. Qualitative analyses reveal patterns in fake news content.

Technical Details

Technological frameworks used: FakeWatch

Models used: Traditional machine learning techniques and Language Models

Data used: Newly curated North American election-related news articles

Potential Impact

Media companies, social media platforms, and electoral campaign strategists could benefit or be disrupted by these insights.

Want to implement this idea in a business?

We have generated a startup concept here: TruthLens.