JSINBIS (Jurnal Sistem Informasi Bisnis)

Detail Cakupan

Abstract The purpose of this research is to do sentiment analysis on tweets data retrieved using ontology framework and using naïve bayes classifier algorithm for classification process. This study is based on the habits of twitter users who frequently writes opinion, expression, or sentiment on a specific product, especially smartphones. These tweets can be used as a basis for sentiment analysis on a particular product. The method used in this study include the use of ontology framework for tweets retrieval that match the domain of the discussion and the use of naïve bayes classification algorithm for data classification. Classification process carried past the 3 pieces of layer classification to fine tune the final result of classification. Three layers of classification used include buzz/promo classification (classifying tweets into buzz and not-buzz tweets), subjectivity classification (classifying not-buzz tweets into subjective and objective tweets), and sentiment classification (classifying subjective tweets into positive, negative, or neutral tweets). The resulted software can classify tweets with high accuracy. This software was trained and tested with the composition of 25:75, 50:50, 75:25 from sample data and tested 10 times for each composition. Average accuracy of the system reached 84.16%, 86.15%, and 87.54% for each composition. The result showed that by employing this system, product marketing stakeholders can determine the level of user sentiment expressed in the form of tweets. The method used in this study could be developed to improve the accuracy of classification systems. Â