Aspect-based sentiment analysis to review products using Naïve Bayes

Product reviews can provide great benefits for consumers and producers. Number of reviews could be ranging from hundreds to thousands and containing various opinions. These make the process of analyzing and extracting information on existing reviews become increasingly difficult. In this research, sentiment analysis was used to analyze and extract sentiment polarity on product reviews based on a specific aspect of the product. This research was conducted in three phases, such as data preprocessing which involves part-of-speech (POS) tagging, feature selection using Chi Square, and classification of sentiment polarity of aspects using Naive Bayes. Based on evaluation results, it is known that the system is able to perform aspect-based sentiment analysis with its highest F1-Measure of 78.12%.Product reviews can provide great benefits for consumers and producers. Number of reviews could be ranging from hundreds to thousands and containing various opinions. These make the process of analyzing and extracting information on existing reviews become increasingly difficult. In this research, sentiment analysis was used to analyze and extract sentiment polarity on product reviews based on a specific aspect of the product. This research was conducted in three phases, such as data preprocessing which involves part-of-speech (POS) tagging, feature selection using Chi Square, and classification of sentiment polarity of aspects using Naive Bayes. Based on evaluation results, it is known that the system is able to perform aspect-based sentiment analysis with its highest F1-Measure of 78.12%.