Abstract: Our information sphere has become increasingly polluted due the increasing presence of misleading and false information. As Wardle and Hossein (2017) highlights in their report [1], this has been possible thanks to a combination of multiple factors, among which the collapse of (local and national) journalism; an increasing sense of distrust in science and evidence-based facts; and the presence of computational amplification tools such as bots. In this talk, I will first offer an overview of work I have conducted in the area of misinformation detection in English, Dutch, and Italian. The second part of the presentation will be mostly dedicated to ongoing work on the reliability of claimants and models to improve the identification of inconsistencies across sources to facilitate the use of NLP technologies in assisting professional fact-checkers.

[1] https://edoc.coe.int/en/media/7495-information-disorder-toward-an-interdisciplinary-framework-for-research-and-policy-making.html

Bio: Dr. Tommaso Caselli is Senior Assistant Professor in Computational Semantics at the Center for Language and Cognition (CLCG) of the Faculty of Arts at the University of Groningen. His main research interests are in event extraction and framing, hate speech and misinformation detection and countering. He is one of the founders of the "Event and Stories in the News" workshop series and the co-editor of the volume "Computational Analysis of Storylines" (CUP, 2021). He has been involved in the organization of several semantic evaluation campaigns for NLP for English and Italian. He has covered (senior) area chair positions at major *CL conferences (COLING, ACL, EMNLP, EACL) and was awarded "Outstanding Area Chair" at ACL 2023. His work is featured in major *CL and journals. He has been awarded two "Outstanding Paper Award" (COLING 2022; ACL 2023).