Sentiment Lexicon Interpolation and Polarity Estimation of Objective and Out-Of-Vocabulary Words to Improve Sentiment Classification on Microblogging

Sentiment analysis has become an important classification task because a large amount of user-generated content is published over the Internet. Sentiment lexicons have been used successfully to classify the sentiment of user review datasets. More recently, microblogging services such as Twitter have become a popular data source in the domain of sentiment analysis. However, analyzing sentiments on tweets is still difficult because tweets are very short and contain slang, informal expressions, emoticons, mistyping and many words not found in a dictionary. In addition, more than 90 percent of the words in public sentiment lexicons, such as SentiWordNet, are objective words, which are often considered less important in a classification module. In this paper, we introduce a hybrid approach that incorporates sentiment lexicons into a machine learning approach to improve sentiment classification in tweets. We automatically construct an Add-on lexicon that compiles the polarity scores of objective words and out-ofvocabulary (OOV) words from tweet corpora. We also introduce a novel feature weighting method by interpolating sentiment lexicon score into uni-gram vectors in the Support Vector Machine (SVM). Results of our experiment show that our method is effective and significantly improves the sentiment classification accuracy compared to a baseline unigram model.