Abstract
With the rapid development of new technologies in smartphones, understanding market trends has become an increasingly difficult task. In these circumstances, online product reviews that can reflect consumer sentiment about the product has been a concern for now. Online review analysis can help sellers understand consumer interests and desires prior to launching a new product. The author wants to contribute to seeing the state of the smartphone market by creating a method to find important aspects of a smartphone. The data source comes from the Amazon e-commerce web with 4 predefined smartphone brands. In this study, the authors used topic modeling with the LDA algorithm and sentiment analysis with VADER to find aspects of a smartphone and its sentiment classification. From the 15 scenarios made in this reserach, it is found 3 aspects that always appear, namely the screen, camera, and battery aspects, so it is concluded that these 3 aspects are the most important of a smartphone based on textual reviews.
Keywords— Topic Modeling; Sentiment Analysis; LDA; ecommerce