Text-Mining Research Group

Challenges and solutions in the opinion summarization of user-generated content

Estimating mass opinion from subjective texts on the Web can beuseful for many real-world applications e.g., marketing, business intelligence,product assessment, decision-support etc. In this paper, we present dierentapproaches to summarizing opinion. We apply these approaches to: a) identifypositive and negative opinions in blog threads in order to produce a list ofarguments in favor and against a given topic and b) summarize the opinionexpressed in reviews. Subsequently, we evaluate the proposed methods on twodistinct datasets and analyze the quality of the obtained results, as well asdiscuss the errors produced. Finally, we conclude that the proposed approachis appropriate in the context of opinion summarization.

Keywords: Sentiment analysis, opinion mining, opinion summarisation, social media

Year: 2012

Download:  Full text 

Alexandra Balahur

E-mail: Alexandra.Balahur@jrc.ec.europa.eu

Mijail Alexandrov Kabadjov

Josef Steinberger

E-mail: jstein@kiv.zcu.cz

Josef is an associated professor at the Department of computer science and engineering at the University of West Bohemia in Pilsen, Czech Republic. He is interested in media monitoring and analysis, mainly automatic text summarisation, sentiment analysis and coreference resolution.

Ralf Steinberger

Andrés Montoyo

E-mail: montoyo@dlsi.ua.es

Automatic Text Summarisation
Authors:	Josef Steinberger, Karel Ježek, Michal Campr, Jiří Hynek
Desc.:	Automatic text summarisation using various text mining methods, mainly Latent Semantic Analysis (LSA).

Multilingual Sentiment Analysis
Authors:	Josef Steinberger
Desc.:	Sentiment analysis of news and social media in multiple languages.