From humour recognition to irony detection: Figurative language processing in social media

The Faculty of Informatics is pleased to announce a seminar given by Paolo Rosso

DATE: Monday, June 17th, 2013
PLACE: USI Lugano Campus, room SI-008, Informatics building (Via G. Buffi 13)
TIME: 16.30

ABSTRACT:
This talk aims at showing how two specific domains of figurative language, humor and irony, could be automatically handled by means of considering linguistic-based patterns. The problem of automatically detecting figurative language needs to consider nearly every aspect of language, from pronunciation to lexical choice, syntactic structure, semantics and conceptualization. Moreover, in the case of irony what is literally said is negated in absence of an explicit negation marker. This makes its detection challenging.

Due to the complexity of the problem, the objective is to start detecting textual patterns that could be applied in their automatic identification. The role of linguistic devices such as ambiguity and incongruity, and meta-linguistic devices such as emotional scenarios and polarity, is also important. In the talk special emphasis will be given to the use of humour and irony in social media (Twitter, Amazon, TripAdvisor etc.). The automatic detection of humour, and especially of irony, would represent valuable knowledge for tasks as diverse as polarity classification, sentiment analysis, opinion mining, information extraction, or decision making.

BIO:
Paolo Rosso received his Ph.D. degree in Computer Science (1999) from Trinity College, University of Dublin, Ireland. He is currently an Associate Professor at Universitat Politècnica de València, Spain. He has published over two hundreds peer reviewed papers, and has been involved in several national and international research projects. His recent research interests are mainly focused on plagiarism detection, irony detection, and author profiling in social media. Since 2009 he has been co-organiser of benchmark activities on plagiarism and text reuse detection, and recently also on author profiling in social media, at CLEF and FIRE information retrieval evaluation fora, in the framework of PAN evaluation lab on uncovering plagiarism, authorship, and social software misuse.

HOST: Prof. Fabio Crestani