Analisis Sentimen Berbasis Aspek pada Review Female Daily Menggunakan TF-IDF dan Naïve Bayes
Clarisa Hasya Yutika, Adiwijaya Adiwijaya, Said Al Faraby
Abstract
The results of a product review will provide considerable benefits for producers or consumers. Female daily is a forum that discusses beauty products. There are many reviews that are obtained every day. Therefore a technique is needed to analyze the results of the review into valuable information. One of the techniques is aspect-based sentiment analysis. Aspect-based sentiment analysis will analyze each text to identify various aspects (attributes or components) then determine the level of sentiment (positive, negative, or neutral) that is appropriate for each aspect. From the results obtained, there are reviews that use multilingual languages. Then the steps taken are to translate the multilingual language into one language only, namely Indonesian. Before the review is processed, preprocessing will be carried out to make it easier to process. Then the word weighting is done using TF-IDF, and the method for classifying sentiments that will be used is Complement Naïve Bayes to overcome unbalanced data. From the test results obtained the best F1-Score of 62,81% for data translated into English and then into Indonesian and not using stopword removal