Multilingual Summarisation and Sentiment Analysis

Multilingual Summarisation and Sentiment Analysis

Summarisation and sentiment analysis are the key NLP technologies which allow monitoring evolving content and opinions in huge amounts of textual data available on the web. Summarisa-tion can address the problem of information overload by extracting and presenting the main con-tent and sentiment analysis can identify opinions expressed towards entities or events. Because there can be found so many opinions, it is needed to aggregate them and present to a user only the most important ones. And this is the case in which summarisation and sentiment analysis have to work together. Studying the problems in multiple languages, besides providing multilin-gual information access, opens new possibilities, like analysing disagreements in reporting across languages or producing more coherent summaries in the case of weakly covered languages. My research focussed mainly on news data, however, the attention is now shifting towards rising social media. This thesis describes the crossing paths of my research of summarisation and sen-timent analysis in multilingual environment.

Keywords: summarization, sentiment analysis, multilinguality

Year: 2013

Download: download Full text [637 kB]

Authors of this publication:

Josef Steinberger


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.

Related Projects:


Automatic Text Summarisation

Authors:  Josef Steinberger, Karel Je┼żek, Michal Campr, Ji┼Ö├ş 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.