To Intervene or Not To Intervene: Cost based Intervention for Combating Fake News

While social media platforms provide valuable and powerful means with which users can share content, comment, and communicate, they also suffer from abuse through the dissemination of fake news and misinformation. While a fair amount of work has been done on detecting fake news, on the complementary problem of limiting its propagation, progress has been modest. Once an item is detected as fake, a social media company can intervene on the item and take an appropriate action, including hard intervention (e.g., removing an account) and soft intervention (e.g., labeling the item as "suspicious"). Given that fake news detectors are not 100% reliable, we study the problem of developing an intervention policy which decides when to intervene on an item. We propose a cost-aware approach for intervention, which determines whether to intervene based on the truthiness and popularity of the item. We define a reward function that seeks to reduce the reach of fake items without affecting the reach of authentic items. Our solution, Solomon, consists of three components - truthiness estimation, popularity estimation (with and without intervention), and intervention policy. Solomon is modular and allows one to plug in any algorithm for each of the components. Our extensive experiments on real and fake news from multiple domains including politics, entertainment,and health show that Solomon can perform effective intervention on news items in these domains.