{"id":621477,"date":"2019-11-15T11:22:32","date_gmt":"2019-11-15T19:22:32","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?post_type=msr-event&p=621477"},"modified":"2025-08-06T11:53:39","modified_gmt":"2025-08-06T18:53:39","slug":"kdd-2019-workshop-on-truth-discovery-and-fact-checking-theory-and-practice","status":"publish","type":"msr-event","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/event\/kdd-2019-workshop-on-truth-discovery-and-fact-checking-theory-and-practice\/","title":{"rendered":"KDD 2019 Workshop on Truth Discovery and Fact Checking: Theory and Practice"},"content":{"rendered":"\n\n

The first workshop on Truth Discovery and Fact Checking: Theory and practice will provide a forum where researchers and practitioners from academia, government and industry can share insights and identify new challenges and opportunities in resolving conflicts, fact-checking and ascertaining credibility of claims. The workshop will be held in Anchorage, Alaska on August 5, 2019 in conjunction with the ACM SIGKDD 2019.Opens in a new tab<\/span><\/p>\n

In recent times, the explosion of information from a variety of sources has made it increasingly important to check the credibility and reliability of the underlying data. Large volumes of data generated from diverse information channels like social media, online news outlets, and crowd-sourcing contribute valuable knowledge. However, this comes with additional challenges to ascertain the credibility of user-generated information, resolving conflicts among heterogeneous data sources, identifying misinformation, etc. Given diverse information about an object (e.g., a natural language claim text, an entity, and an SPO like triple) from heterogeneous and multi-modal sources like relational data, natural language text, images and video: how do we identify high quality and trustworthy information and information sources? How can we leverage Knowledge Bases and external evidence sources from the web for reasoning, explaining and validating claims while dealing with their limitations regarding incompleteness and emerging facts? How can we generate human-interpretable explanations for the models’ verdict as opposed to black box methods? In order to answer these questions, this workshop encourages submissions to focus on big ideas for resolving conflicts, fact-checking and ascertaining credibility of claims in heterogeneous and multi-modal sources of information — focusing both on unstructured texts, natural language claims, relational data and knowledge graphs.Opens in a new tab<\/span><\/p>\n