5001

Automatic Sentiment Monitoring of Specific Topics in the Blogosphere

Fernanda Sant Anna Pimenta, Darko Obradovic, Rafael Schirru, Stephan Baumann, Andreas Dengel

Proceedings of the 1st Workshop on Dynamic Networks and Knowledge Discovery Workshop on Dynamic Networks and Knowledge Discovery (DyNaK-2010), located at ECML-PKDD 2010, September 24, Barcelona, Spain , Vol: 655 , CEUR-WS.org , 2010
The classification of a text according to its sentiment is a task of raising relevance in many applications, including applications re- lated to monitoring and tracking of the blogosphere. The blogosphere provides a rich source of information about products, personalities, tech- nologies, etc. The identification of the sentiment expressed in articles is an important asset to a proper analysis of this user-generated data. In this paper we focus on the task of automatic determination of the po- larity of blogs articles, i. e., the sentiment analysis of blogs. In order to identify whether a piece of text expresses a positive or negative opin- ion, an approach based on word spotting was used. Empirical results on different domains show that our approach performs well if compared to costly and domain-specific approaches. In addition to that, if we consider an aggregation of a set of documents and not the polarity of each indi- vidual document, we can achieve an accuracy distribution around 90% for specific topics of a certain domain.

Show BibTex:

@inproceedings {
       abstract = {The classification of a text according to its sentiment is a task of raising relevance in many applications, including applications re- lated to monitoring and tracking of the blogosphere. The blogosphere provides a rich source of information about products, personalities, tech- nologies, etc. The identification of the sentiment expressed in articles is an important asset to a proper analysis of this user-generated data. In this paper we focus on the task of automatic determination of the po- larity of blogs articles, i. e., the sentiment analysis of blogs. In order to identify whether a piece of text expresses a positive or negative opin- ion, an approach based on word spotting was used. Empirical results on different domains show that our approach performs well if compared to costly and domain-specific approaches. In addition to that, if we consider an aggregation of a set of documents and not the polarity of each indi- vidual document, we can achieve an accuracy distribution around 90% for specific topics of a certain domain.},
       number = {}, 
       month = {9}, 
       year = {2010}, 
       title = {Automatic Sentiment Monitoring of Specific Topics in the Blogosphere}, 
       journal = {}, 
       volume = {655}, 
       pages = {}, 
       publisher = {CEUR-WS.org}, 
       author = {Fernanda Sant Anna Pimenta, Darko Obradovic, Rafael Schirru, Stephan Baumann, Andreas Dengel}, 
       keywords = {sentiment analysis blogosphere nlp},
       url = {http://kdd.di.unito.it/DyNaK2010/, http://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=dynak2010_submission_2.pdf&file_id=uploads_824}
}