Designing a Ranking System for Product Search Engine Based on Mining UGC

With the spread of e-commerce platforms, it becomes extremely difficult for the consumer to choose the right product from a large number of identical products, and different sellers based only on his/her own experience, product pictures or product metadata. Customers reviews present a rich and valuable source of information for potential consumers and manufacturers which can be very helpful in the decision process, but reading all of the available reviews is a hard task and time-consuming. Thus, the automated mining of these reviews and extracting product features in order to generate a raking system present a valuable and useful tool for consumers to make a well-informed decision. In this paper, we propose a ranking system for product search engine based on mining customers reviews. The product features pairs are extracted using Stanford typed dependencies. The evaluation process of the proposed system has passed through two levels: first measuring of accuracy of product feature extraction and classification, and the second one is the determination of the efficiency of the search results and the usability of visual summarization. The results show a high level of accuracy in feature/opinion pairs extraction and high level of participant satisfaction with the ranking and the summarization.