Sentiment analysis system for Indonesia online retail shop review using hierarchy Naive Bayes technique
Cut Fiarni, Herastia Maharani, Rino Pratama · 2016
The rapid growth of internet user and the popularity of social media network has changed how people interact and doing everyday activities. Indonesia Small Medium Enterprise Organizations, such as the retail industry has also started to uses various social media to market their product online. The rapid growth of internet user and the popularity of social media network has led to big data of online opinion. Analysis on these opinions is very important because it can extract knowledge that can be the basis in making business decisions for the organizations. The problem is Indonesian citizen communicate in Bahasa and local languages, not to mention slang languages. So to build a sentiment analysis system is not easy because it has to be able to identify words and classify its sentiment. To overcome this problem, a sentiment analysis system that able to process opinions from social media using text mining is developed. This proposed approach would use feature extraction and selection to select words from learning dataset of Indonesian corpus and then classifying them to the respective class of target objects and sentiment. Then, we adopt the Naïve Bayes Classifier technique, with 3 sentiment classifications, aspects of online retail shop, and polarity of sentiment (positive, negative and neutral) and the polarity of the aspects of online retail shop. Results from this study shows that the sentiment analysis system for clothing product on social media using Naïve Bayes Classifier method is able to classify user opinions with 97.25% precision, 89.83% recall, and 89.21% accuracy.