Fecha: 21 de Junio de 2016

Ponente: Anastasia Giachanou, (University of Lugano, Suiza)

Lugar de celebración: Sala 1.03, ETSI Informática, UNED (mapa)

Resumen:

Twitter which is one of the most popular microblogs has emerged as a vast repository of information and opinion on various topics. However, all this opinionated information is hidden within a vast amount of data and it is nearly impossible for a person to extract useful information. Twitter-based opinion retrieval aims to identify tweets that are relevant to a user's query and also express opinion about it. Another powerful tool is tracking opinion over time that can be used for sentiment prediction or to detect the possible reasons of a sentiment change. In the first part of this talk, I will describe how to leverage topic-specific stylistic variations such as emoticons, emphatic lengthening and slang terms to retrieve tweets that are both relevant and opinionated about a particular topic. In the second part of my talk, I will focus on the problem of sentiment evolution and how conventional time series methods can be used to address it.