In a context where misinformation spreads rapidly on social media, especially during election periods, researchers at Ben-Gurion University of the Negev (BGU) in Israel have developed an innovative tool that promises to improve the efficiency of the fight against fake news.
The team, led by Dr. Nir Grinberg and Professor Rami Puzis of BGU's Department of Software Engineering and Information Systems, proposed an approach that prioritizes monitoring sources of misinformation rather than focusing on individual posts.
This method, based on audience analysis models and machine learning, is much more effective than traditional strategies. According to the study, the models outperformed current methods by 33% when analyzing historical data, and by up to 69% when applied in real time to emerging sources.
“Our goal was to help fact-checkers better focus their attention, because they're currently overburdened and unable to review all the content circulating. We developed a system that allows them to identify problematic sources more quickly and with less effort,” Grinberg explained.
One of the system's main advantages is that it maintains the same level of accuracy as current methods, but requires less than a quarter of the resources. The study was recently published in the proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, one of the world's leading conferences in the field of artificial intelligence and data analytics.