"Credibility detection, deception detection and author profiling" by Prof Paolo ROSSO (Universitat Politecnica de Valencia, Spain)

Date : 1 Mars 2020
Lieu : Salle de séminaire à la faculté des NTICs
Organisé par l'équipe SCAL
Mots clés
Information Retrieval Evaluation Author Profiling Deception Detection in Arabic Fake news detection LSTM models with emotional signals Credibility assessment Shared tasks in Arabic


In the first part of the talk I would briefly describe some of our recent works on how emotions play a key role in deceiving the reader,
concretely we investigated the role of emotional signals in fake news detection. We proposed LSTM models that incorporate emotional signals
extracted from the text of the claims to differentiate between credible and non-credible ones. Experiments on real world datasets
show the importance of emotional signals for credibility assessment.

In the second part of the talk I will present the results of shared tasks in Arabic that we recently organised at the Forum for
Information Retrieval Evaluation as one of the research activities of the Arabic Author Profiling for Cyber-Security project (Qatar National
Research Fund). I will focus on the Author Profiling and Deception Detection in Arabic (APDA) shared task where we addressed: (i) to
profile age, gender and native language of a Twitter user; (ii) to determine whether an Arabic text is deceptive or not in two different
genres: Twitter and news headlines.



Paolo Rosso ( is full professor at  the Universitat Politecnica de Valencia, Spain where he is also member 
of the PRHLT research center. His research interests focus mainly on author profiling, irony detection, opinion spam detection, and 
plagiarism detection. Since 2009 he has been involved in the organisation of PAN benchmark activities at CLEF and at FIRE 
evaluation forums, mainly on plagiarism / text reuse detection and author profiling. At SemEval he has been co-organiser of shared tasks 
on sentiment analysis of figurative language in Twitter (2015), and on multilingual detection of hate speech against immigrants and women in 
Twitter (2019). He has been PI of national and also international research projects funded by EC and U.S. Army Research Office. 
Recently, in collaboration with Carnegie Mellon University, he is involved in a project funded by Qatar National Research Fund on author 
profiling for cyber-security, which aims to profile who is behind to threat messages. He serves as deputy steering committee chair for the 
CLEF conference and as associate editor for the Information Processing & Management journal. He has been chair of *SEM-2015, and organization 
chair of CERI-2012, CLEF-2013 and EACL-2017. He is the author of 400+ papers, published in journals, book chapters, conference and workshop