Nowadays, many people prefer to purchase through online websites. Usually, those people start with reading user reviews and comments before making a purchase decision. The user reviews are considered powerful sources of information about products, in which users share opinions and previous experiences on using these products. However, these reviews are mostly textual and uncategorized. Thus, new customers need to read a massive amount of reviews, one by one, in order to make a decision. In specific, there is a research gap text analysis i.e. LDA in unsupervised learning produce inaccurate results. This project attempts to bridge this gap and combine two approaches of topic modeling which are unsupervised and supervised learning, i.e., semi-supervised learning, for classifying the reviews to enhance text analysis. In addition, it makes classification based on sentiment analysis and visualize the reviews as a dashboard.