Fine Grained Sentiment Classification of Customer Reviews Using Computational Intelligent Technique

Online reviews are now popularly used for judging quality of product or service and influence decision making of users while selecting a product or service. Due to innumerous number of customer reviews on the web, it is difficult to summarize them which require a faster opinion mining system to classify the reviews. Many researchers have explored various supervised and unsupervised machine learning techniques for binary classification of reviews. Compared to these techniques, fuzzy logic can provide a straightforward and comparatively faster way to model the fuzziness existing between the sentiment polarities classes due to the ambiguity present in most of the natural languages. But the fuzzy logic techniques are less explored in this domain. Hence in this paper, a fuzzy logic model based on the most popularly known sentiment based lexicon SentiWordNet has been proposed for fine grained classification of the reviews into weak positive, moderate positive, strong positive, weak negative, moderate negative and strong negative classes. Experiments have been conducted on datasets containing reviews of electronic products namely smart phones, LED TV and laptops and have shown to provide fine grained classification accuracy approximately in the range of 74% to 77%. KeywordSentiment analysis, Fine grained Classification, Fuzzy Logic, SentiWordNet, Online reviews