Sentiment Classification of Movie and Product Reviews Using Contextual Valence Shifters

We present a method for determining the sentiment expressed by a customer review. The semantic orientation of a review can be positive, negative, or neutral. Our method counts positive and negative terms, but also takes into account contextual valence shifters, such as negations and intensifiers. Tests are done taking both negations and intensifiers into account, and also using only negations without intensifiers. Negations are used to reverse the semantic polarity of a particular term, while intensifiers are used to change the degree to which a term is positive or negative. We use the General Inquirer in order to identify positive and negative terms, as well as negations, overstatements, and understatements. We also test the impact of adding extra positive and negative terms from other sources, including a dictionary of synonym differences and a very large web corpus. To compute the corpus-based values of the semantic orientation of individual terms we use their association scores with a small group of positive and negative terms. We show that including contextual valence shifters improves the accuracy of the classification.

[1]  Kathleen R. McKeown,et al.  Predicting the semantic orientation of adjectives , 1997 .

[2]  Bo Pang,et al.  A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts , 2004, ACL.

[3]  Edoardo M. Airoldi,et al.  Sentiment Extraction from Unstructured Text using Tabu Search-Enhanced Markov Blanket , 2004 .

[4]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[5]  Ellen Riloff,et al.  Learning Extraction Patterns for Subjective Expressions , 2003, EMNLP.

[6]  Marshall S. Smith,et al.  The general inquirer: A computer approach to content analysis. , 1967 .

[7]  Michael L. Littman,et al.  Measuring praise and criticism: Inference of semantic orientation from association , 2003, TOIS.

[8]  Michael L. Littman,et al.  Unsupervised Learning of Semantic Orientation from a Hundred-Billion-Word Corpus , 2002, ArXiv.

[9]  Sergio Bolasco,et al.  Experiments on semantic categorisation of texts: analysis of positive and negative dimension , 2004 .

[10]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[11]  Charles L. A. Clarke,et al.  Passage retrieval vs. document retrieval for factoid question answering , 2003, SIGIR.

[12]  Janyce Wiebe,et al.  Learning Subjective Language , 2004, CL.

[13]  Peter D. Turney.  Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews , 2002, ACL.

[14]  Annie Zaenen,et al.  Contextual Valence Shifters , 2006, Computing Attitude and Affect in Text.

[15]  Michael Gamon,et al.  Sentiment classification on customer feedback data: noisy data, large feature vectors, and the role of linguistic analysis , 2004, COLING.

[16]  Maite Taboada,et al.  Analyzing Appraisal Automatically , 2004 .

[17]  Graeme Hirst,et al.  Generating More-Positive and More-Negative Text , 2006, Computing Attitude and Affect in Text.

[18]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.