Towards a Robust Metric of Polarity

@incollection{citeulike:2461576, abstract = {This chapter describes an automated system for detecting polar expressions about a specified topic. The two elementary components of this approach are a shallow NLP polar language extraction system and a machine learning based topic classifier. These components are composed together by making a simple but accurate collocation assumption: if a topical sentence contains polar language, the polarity is associated with the topic. We evaluate our system, components and assumption on a corpus of online consumer messages.}, author = {Nigam, Kamal and Hurst, Matthew }, citeulike-article-id = {2461576}, journal = {Computing Attitude and Affect in Text: Theory and Applications}, keywords = {opinion-classification, sentiment-classification}, pages = {265--279}, posted-at = {2008-03-03 18:44:34}, priority = {5}, title = {Towards a Robust Metric of Polarity}, url = {http://dx.doi.org/10.1007/1-4020-4102-0\_20}, year = {2006} }

TY - CHAP ID - citeulike:2461576 L3 - citeulike-article-id:2461576 TI - Towards a Robust Metric of Polarity JF - Computing Attitude and Affect in Text: Theory and Applications SP - 265 EP - 279 N2 - This chapter describes an automated system for detecting polar expressions about a specified topic. The two elementary components of this approach are a shallow NLP polar language extraction system and a machine learning based topic classifier. These components are composed together by making a simple but accurate collocation assumption: if a topical sentence contains polar language, the polarity is associated with the topic. We evaluate our system, components and assumption on a corpus of online consumer messages. KW - opinion-classification KW - sentiment-classification AU - Nigam, Kamal AU - Hurst, Matthew PY - 2006/// UR - http://dx.doi.org/10.1007/1-4020-4102-0_20 ER -