Computational Fact Checking from Knowledge Networks

TLDR

Traditional fact checking cannot keep up with the volume of online information, so computational fact checking could enhance our ability to evaluate dubious claims. The study aims to approximate human fact checking by finding the shortest path between concept nodes using semantic proximity metrics on knowledge graphs. The method frames fact checking as a network problem, employing efficient computational techniques to evaluate tens of thousands of claims from a Wikipedia‑derived knowledge graph. True statements receive higher support than false ones, indicating the method is a promising step toward scalable computational fact checking that could mitigate misinformation.

Abstract

Traditional fact checking by expert journalists cannot keep up with the enormous volume of information that is now generated online. Computational fact checking may significantly enhance our ability to evaluate the veracity of dubious information. Here we show that the complexities of human fact checking can be approximated quite well by finding the shortest path between concept nodes under properly defined semantic proximity metrics on knowledge graphs. Framed as a network problem this approach is feasible with efficient computational techniques. We evaluate this approach by examining tens of thousands of claims related to history, entertainment, geography, and biographical information using a public knowledge graph extracted from Wikipedia. Statements independently known to be true consistently receive higher support via our method than do false ones. These findings represent a significant step toward scalable computational fact-checking methods that may one day mitigate the spread of harmful misinformation.