Learning Lexical Subjectivity Strength for Chinese Opinionated Sentence Identification

摘要

Lexical subjectivity strength has proven to be of great value to subjectivity classification. However, the quantitative calculation of lexical subjectivity strength has not yet been much explored. This paper presents a fuzzy set based approach to automatically learn lexical subjectivity strength for Chinese opinionated sentence identification. To approach this task, log-linear probabilities are employed to extract a set of subjective words from opinionated sentences, and three fuzzy sets, namely low-strength subjectivity, medium-strength subjectivity and high-strength subjectivity, are then defined to represent their respective classes of subjectivity strength. Furthermore, three membership functions are built to indicate the degrees of subjective words in different fuzzy sets. Finally, the acquired lexical subjective strength is further exploited to perform subjectivity classification. The experimental results on the NTCIR-7 MOAT data demonstrate that the introduction of lexical subjective strength is beneficial to subjectivity classification.