TY - GEN
T1 - Automatic construction of a context-aware sentiment lexicon
T2 - 20th International Conference on World Wide Web, WWW 2011
AU - Lu, Yue
AU - Castellanos, Malu
AU - Dayal, Umeshwar
AU - Zhai, Cheng Xiang
PY - 2011
Y1 - 2011
N2 - The explosion of Web opinion data has made essential the need for automatic tools to analyze and understand people's sentiments toward different topics. In most sentiment analysis applications, the sentiment lexicon plays a central role. However, it is well known that there is no universally optimal sentiment lexicon since the polarity of words is sensitive to the topic domain. Even worse, in the same domain the same word may indicate different polarities with respect to different aspects. For example, in a laptop review, \large" is negative for the battery aspect while being positive for the screen aspect. In this paper, we focus on the problem of learning a sentiment lexicon that is not only domain specific but also dependent on the aspect in context given an unlabeled opinionated text collection. We propose a novel optimization framework that provides a unified and principled way to combine different sources of information for learning such a context-dependent sentiment lexicon. Experiments on two data sets (hotel reviews and customer feedback surveys on printers) show that our approach can not only identify new sentiment words specific to the given domain but also determine the different polarities of a word depending on the aspect in context. In further quantitative evaluation, our method is proved to be effective in constructing a high quality lexicon by comparing with a human annotated gold standard. In addition, using the learned context-dependent sentiment lexicon improved the accuracy in an aspect-level sentiment classification task.
AB - The explosion of Web opinion data has made essential the need for automatic tools to analyze and understand people's sentiments toward different topics. In most sentiment analysis applications, the sentiment lexicon plays a central role. However, it is well known that there is no universally optimal sentiment lexicon since the polarity of words is sensitive to the topic domain. Even worse, in the same domain the same word may indicate different polarities with respect to different aspects. For example, in a laptop review, \large" is negative for the battery aspect while being positive for the screen aspect. In this paper, we focus on the problem of learning a sentiment lexicon that is not only domain specific but also dependent on the aspect in context given an unlabeled opinionated text collection. We propose a novel optimization framework that provides a unified and principled way to combine different sources of information for learning such a context-dependent sentiment lexicon. Experiments on two data sets (hotel reviews and customer feedback surveys on printers) show that our approach can not only identify new sentiment words specific to the given domain but also determine the different polarities of a word depending on the aspect in context. In further quantitative evaluation, our method is proved to be effective in constructing a high quality lexicon by comparing with a human annotated gold standard. In addition, using the learned context-dependent sentiment lexicon improved the accuracy in an aspect-level sentiment classification task.
KW - Opinion mining
KW - Optimization
KW - Sentiment analysis
KW - Sentiment lexicon
UR - http://www.scopus.com/inward/record.url?scp=83655166226&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=83655166226&partnerID=8YFLogxK
U2 - 10.1145/1963405.1963456
DO - 10.1145/1963405.1963456
M3 - Conference contribution
AN - SCOPUS:83655166226
SN - 9781450306324
T3 - Proceedings of the 20th International Conference on World Wide Web, WWW 2011
SP - 347
EP - 356
BT - Proceedings of the 20th International Conference on World Wide Web, WWW 2011
Y2 - 28 March 2011 through 1 April 2011
ER -