Deim Seminar
Title
Discovering Relevant Opinions in Twitter with Argumentation and Probabilistic valued relationships
Conferenciant
Ramon Bejar
Professor/a organitzador/a
Aïda Valls Mateu
Institution
Universitat de Lleida
Date
05-12-2018 12:00
Summary
Dr. Bejar is associate professor at the department of Informatics and Industrial Engineering (UdL). He is a member of the Board of the Catalan Association for Artificial Intelligence (ACIA). His research is focused on Logics, Argumentation and Constrained Satisfaction problems.
He will present his last work on the analysis of Twitter discussions. Twitter is one of the most widely used social networks when it comes to sharing and criticizing relevant news and events. In order to understand the major accepted and rejected opinions in different domains by Twitter users, we present an analysis system based on valued abstract argumentation to model and reason about the social acceptance of tweets in a discussion.
We consider two different sources of information: the support for each tweet and the criticism/support relationship between tweets. The support for each tweet is mapped to a weight, and the criticism/support relationship between a pair of tweets is modeled with a probability vector. Our system also uses an uncertainty threshold probability, to filter our relationships that are considered to be not strong enough. Finally, the system uses a reasoning algorithm to discover the
winning (accepted) tweets in a discussion.
Place
Aula A215
Language
Anglès
