ANALISIS SENTIMEN PADA REVIEW PRODUK SEBAGAI REKOMENDASI CUSTOMER MENGGUNAKAN KOMBINASI K-MEANS DAN ALGORITMA NAÏVE BAYES CLASSIFIER

In e-commerce shopee the process of selling and buying continues to run every day and the comments given by consumers will increase more and more. Comments given by consumers will be a reference / review of a product that has been purchased by consumers. consumers freely give a review that contains positive comments and negative comments in the comments column listed on the shopee e-commerce website. With the above problems researchers will conduct research with sentiment analysis methods to differentiate classes in product review comments which include positive comment class or negative comment class using k-means combination and naive bayes classifier. K-means is used to determine class grouping, naive bayes classifier is used to get the value of the akurai. The results obtained based on clustering k-means include getting 116 negative comments on product reviews and 37 negative comments on product reviews. Accuracy results obtained from product review comment data amounted to 77.12%. Thus the accuracy values using k-means and naive bayes classifier without manual data get higher accuracy values compared to using k-means, naive bayes classifier and manual data get lower accuracy results that is 56.86%. From the results above the most comments are negative comments as much as 116 product review comment data, from the results of the study it can be concluded that one of the products from spatuafa called high heels women know the FX18 connective tape the product condition is not good enough because of the high negative comments compared to positive comments.