Sentiment analysis of online Chinese comments based on statistical learning combining with pattern matching

摘要

Sentiment analysis, as a branch of unstructured data mining, has interested people greatly. Sentimentanalysis based on machine learning method usually considers less sentimental featureextraction. This article presents a method based on machine learning combining with patternmatching for sentiment analysis.We conduct basic sub-word first, and then designed the keywordextraction strategy.We designed someemotional expression patterns.After the success matchingto those patterns,we get emotional features, which are in the form of sequence. For each featurepattern, we calculated the value of emotional tendency, and finally to obtain the emotional tendencyof the web comment based on machine-learning method. The experiment result shows themethod can improve the classification performances compared to using regular machine-learningmethod.