Fake News Detection in Social Networks via Crowd Signals

Abstract

Our work considers leveraging crowd signals for detecting fake news and is motivated by tools recently introduced by Facebook that enable users to flag fake news. By aggregating users' flags, our goal is to select a small subset of news every day, send them to an expert (e.g., via a third-party fact-checking organization), and stop the spread of news identified as fake by an expert. The main objective of our work is to minimize the spread of misinformation by stopping the propagation of fake news in the network. It is especially challenging to achieve this objective as it requires detecting fake news with high-confidence as quickly as possible. We show that in order to leverage users' flags efficiently, it is crucial to learn about users' flagging accuracy. We develop a novel algorithm, Detective, that performs Bayesian inference for detecting fake news and jointly learns about users' flagging accuracy over time. Our algorithm employs posterior sampling to actively trade off exploitation (selecting news that maximize the objective value at a given epoch) and exploration (selecting news that maximize the value of information towards learning about users' flagging accuracy). We demonstrate the effectiveness of our approach via extensive experiments and show the power of leveraging community signals for fake news detection.

The facts of fake news: A research review

“…These findings should be able to guide efforts to address the problem of fake news. For example, studies in computer science and engineering have proposed ways to detect fake news using automation (e.g., Dey, Rafi, Parash, Arko, & Chakrabarty, 2018;Kim, Tabibian, Oh, Schlkopf, & Rodriguez, 2018;Tschiatschek, Singla, Rodriguez, Merchant, & Krause, 2018). In mass communication studies, a widely researched area when it comes to addressing fake news is that of fact checking.…”

Will the crowd game the algorithm? Using layperson judgments to combat misinformation on social media by downranking distrusted sources

“…Kim et al propose CURB, a marked temporal points process framework that selects news to be fact-checked by solving a stochastic optimal control problem [20]. Tschiatschek et al propose DETEC-TIVE, an online algorithm that performs Bayesian inference to jointly learn user flagging activity and detect misinformation [44]. The approach we study differs from these approaches by focusing on evaluating news sources, rather than individual articles.…”

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

“…In literature, researchers focused on four topics regarding fake news: characterization (i.e., types of fake news), motivation, circulation, and countermeasures [21,52]. A large body of work has been done on fake news identification [3,36,40,49] by exploiting multiple content-related and social-related components. However, we notice that the fake news still has been widely spread even after early detection [11].…”