Performance Investigation of Feature Selection Methods

Sentiment analysis or opinion mining has become an open research domain after proliferation of Internet and Web 2.0 social media. People express their attitudes and opinions on social media including blogs, discussion forums, tweets, etc. and, sentiment analysis concerns about detecting and extracting sentiment or opinion from online text. Sentiment based text classification is different from topical text classification since it involves discrimination based on expressed opinion on a topic. Feature selection is significant for sentiment analysis as the opinionated text may have high dimensions, which can adversely affect the performance of sentiment analysis classifier. This paper explores applicability of feature selection methods for sentiment analysis and investigates their performance for classification in term of recall, precision and accuracy. Five feature selection methods (Document Frequency, Information Gain, Gain Ratio, Chi Squared, and Relief-F) and three popular sentiment feature lexicons (HM, GI and Opinion Lexicon) are investigated on movie reviews corpus with a size of 2000 documents. The experimental results show that Information Gain gave consistent results and Gain Ratio performs overall best for sentimental feature selection while sentiment lexicons gave poor performance. Furthermore, we found that performance of the classifier depends on appropriate number of representative feature selected from text.

Using Self-Organizing Maps for Sentiment Analysis

Web 2.0 services have enabled people to express their opinions, experience and feelings in the form of user-generated content. Sentiment analysis or opinion mining involves identifying, classifying and aggregating opinions as per their positive or negative polarity. This paper investigates the efficacy of different implementations of Self-Organizing Maps (SOM) for sentiment based visualization and classification of online reviews. Specifically, this paper implements the SOM algorithm for both supervised and unsupervised learning from text documents. The unsupervised SOM algorithm is implemented for sentiment based visualization and classification tasks. For supervised sentiment analysis, a competitive learning algorithm known as Learning Vector Quantization is used. Both algorithms are also compared with their respective multi-pass implementations where a quick rough ordering pass is followed by a fine tuning pass. The experimental results on the online movie review data set show that SOMs are well suited for sentiment based classification and sentiment polarity visualization.