Tag Archives: fact-checking

Computational fact-checking

computational-fact-checkingTraditional 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.

We have shown that the complexities of fact checking can be captured 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. Such approaches can be designed to not only be scalable and effective at assessing veracity of dubious claims, but also to boost a human fact checker’s productivity by surfacing relevant facts and patterns to aid their analysis. We evaluated 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.

We also developed a network-flow based approach. We showed that computational fact checking amounts to finding a “knowledge stream” that emanates from a subject node and flows toward an object node through paths connecting them. Evaluation on a range of real-world and hand-crafted datasets of facts related to entertainment, business, sports, geography and more reveals that this network-flow model can be very effective in discerning true statements from false ones, outperforming existing algorithms on many test cases. Moreover, the model is expressive in its ability to automatically discover several useful path patterns and surface relevant facts that may help a human fact checker corroborate or refute a claim.

These findings represent a significant step toward scalable computational fact-checking methods that may one day mitigate the spread of harmful misinformation.

Fil Menczer, PI
Fil Menczer
Prashant Shiralkar
Prashant Shiralkar
Giovanni Luca Ciampaglia
Giovanni Luca Ciampaglia
Sandro Flammini
Sandro Flammini
Luis Rocha
Luis Rocha
Johan Bollen
Johan Bollen
Mihai Avram
Mihai Avram

 

New CASCI papers on Complex Networks

Network Science Journal
Network Science

Read new papers from CASCI on developing the mathematical toolbox available to deal with computing distances on weighted graphs, applying distance closures for computational fact checking, and computing multi-scale integration in brain networks:

T. Simas and L.M. Rocha [2015].”Distance Closures on Complex Networks”. Network Science, doi:10.1017/nws.2015.11.

G.L. Ciampaglia, P. Shiralkar, L.M. Rocha, J. Bollen, F. Menczer, A. Flammini [2015]. “Computational fact checking from knowledge networks.” PLoS One. In Press. arXiv:1501.03471.

A. Kolchinsky, M. P. Van Den Heuvel, A. Griffa, P. Hagmann, L.M. Rocha, O. Sporns, J. Goni [2014]. “Multi-scale Integration and Predictability in Resting State Brain Activity”. Frontiers in Neuroinformatics, 8:66. doi: 10.3389/fninf.2014.00066.