Browsing and analyzing the "web of claims": characteristics, biases and evolution of fact-checked claims
This event is over!
The aim of the Research MIPS conferences is to raise community awareness of new themes and technological innovations.
Aimed at a wide audience - students and researchers from all disciplines - they feature the multidisciplinary expertise of the MIPS cluster, its partner clusters and structures, as well as national and international teams.
They are held on the first Friday of each month at 11 a.m., and are followed by a buffet for further discussion.
BROWSING AND ANALYSING THE WEB OF CLAIMS: CHARACTERISTICS, BIASES AND EVOLUTION OF FACT-CHECKED CLAIMS
SURVIVING AND ANALYZING THE WEB OF CLAIMS: CHARACTERISTICS, BIAISES AND EVOLUTION OF FACT-VERIFIED CLAIMS
Konstantin Todorov, LIRMM, Montpellier
How do falsehoods spread on the web? This question, tied to the spread of fake newsand biased discourse, has gained interest across fields from social sciences to AI.Online discourse-claims and opinions shared online with their contexts (authors,entities, events)-offers valuable insights. However, knowledge graphs of today lackinformation about claims and related discourse, limiting their utility for accessing andreusing this data. In this talk, I will introduce ClaimsKG, a knowledge graph of fact-checked claims enriched with metadata like truth labels, authors, topics, andreferences. Built from fact-checking portals and structured using a purpose-built datamodel, ClaimsKG provides ground truth data for analyzing societal debates on theweb. I will demonstrate tools developed for ClaimsKG that facilitate claim explorationand statistical analysis, exploring the biases and evolution of fact-checked claims onthe web. Finally, I will place a specific emphasis on ongoing work in modeling andtracing science-related discourse, showcasing the importance of this topic and theneed for novel models specifically tailored to scientific discourse in online platforms.

Receive a weekly summary of the UM agenda
* By entering your e-mail address you agree to receive the weekly UM agenda summary by e-mail and you acknowledge our privacy policy. You can unsubscribe at any time using the unsubscribe link or by contacting us by e-mail.