Product Recommendation System Using Opinion Mining on Vietnamese Reviews

Opinion mining (also known as sentiment analysis) through customers’ reviews or feedbacks which can identify the user opinion about different product features has received a lot of attention exhibited in numerous studies. The majority of recommender systems have recommended products based only on overall evaluation and primarily based on expert’s evaluation. In this work, we propose a method to explore Vietnamese reviews extracted from e-commerce websites in Vietnam to provide suggestions in products selection based on products’ features/functions. The proposed approach introduces a topic-based model to identify products’ features which are mentioned in customer comments/reviews. The proposed system is implemented with the integration combining the VietSentiWordnet to calculate the importance scores for the features of each product. We also construct a product recommendation database which can store customers preference and purchases history. The work is analysed on more than 2,000 Vietnamese comments/reviews about laptop products and is expected to be feasible to apply in practical cases.