The Challenges of Opinion Retrieval on User Generated Content

Professor Fabio Crestani  of University of Lugano  will present the Department of Computer Science colloquim with a talk entitled, "The Challenges of Opinion Retrieval on User Generated Content".

Opinion retrieval is concerned with finding documents that are both relevant and opinionated to a user information need. Information retrieval (IR) has dealt with relevance for a long time, but opinion is a more recent issue whose solution seems to go beyond what can be achieved with standard IR techniques. In this talk I will present some of the challenges that opinion retrieval brings to IR, in particular in the context of the retrieval of user generated content, like blogs and tweets. I will focus on how we can find acceptable solutions to this problem within IR, without resorting to Natural Language Processing techniques that would not scale up to the size of the collections we deal with in IR. In this context I will report on the results of a number of past and current projects we are working in at USI.  

Fabio Crestani has been a Full Professor at the Faculty of Informatics of the Universita’ della Svizzera Italiana (USI) in Switzerland since 2007.  Previously he was a professor at the University of Strathclyde in Glasgow, UK. Fabio is an internationally recognised researcher in Information Retrieval, Text Mining and Digital Libraries. In these areas he has published over two hundred refereed papers on both theoretical and experimental topics. 

Thu, 30 Mar 2017 - 13:00

Computer Science Lecture Theatre 302, Upper Campus, UCT