[cs-talks] Wed-4/26 Hariri Institute Colloquium: Online Political Speech & Fact Checking

Barnes, Kaitlin S ksbarnes at bu.edu
Fri Apr 21 10:46:33 EDT 2017

Join the Hariri Institute for a colloquium on the topics of online political speech and the need for fact checking tools; Giovanni Luca Ciampaglia (Indiana University) and Brian Ulicny (Thomson Reuters) will present their work on computational fact checking and real-time assessment of information credibility.

Wednesday, April 26, 2017
11:00am – 12:00pm
Hariri Institute for Computing, Seminar Room
111 Cummington Mall; Boston, MA
Event URL: http://www.bu.edu/hic/2017/04/21/institute-hosts-426-colloquium-on-online-political-speech-fact-checking/

Giovanni Luca Ciampaglia <http://glciampaglia.com/>
Research Scientist
Center for Complex Networks and Systems Research
Indiana University School of Informatics and Computing

Computational Fact Checking from Knowledge Networks

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. In this work, 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.

Brian Ulicny<https://blogs.thomsonreuters.com/answerson/authors/brian-ulicny/>
Senior Director of Data Science, Thomson Reuters
Founding Member & Head of Thomson Reuters Labs – Boston

Real-Time Detection and Assessment of Credibility and Newsworthiness of Social Media Stories

Abstract: There is a pressing need for algorithmic assessments of information on social media to keep up with its volume and velocity. This presentation will provide an overview of the algorithms and design decisions behind Reuters News Tracer. Reuters News Tracer is a new event detection suite that attempts to detect and assess credible and newsworthy stories on social media in real time. The Social Analytics and News Event (SANE) system was created by Thomson Reuters Research and Development in collaboration with Reuters News. The objective is to listen to and extract information from social media conversations, Twitter in particular. Proprietary algorithms filter out the noise in this information (chat, spam, advertisements), separate and identify facts and opinions, detect breaking news events, organize them by topic, and assess the credibility of those reports. The system is designed to detect credible and newsworthy events in real time as soon as possible after they are reported in social media, and ideally before they become widely reported by mainstream media. This presentation will focus on the challenges of assessing social media in real or near-real time.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs-mailman.bu.edu/pipermail/cs-talks/attachments/20170421/d5be475d/attachment.html>

More information about the cs-talks mailing list