A Large-Scale Reviews-Driven Multi-Criteria Product Ranking Approach Based on User Credibility and Division Mechanism

Massive online reviews provide consumers with the convenience of obtaining product information, but it is still worth exploring how to useful and reliable rankings. The existing ranking methods do not fully mine user rating, text comment information obtain scientific reasonable aggregation methods. Therefore, this study constructs a credibility model proposes large-scale method new method. First, in order aggregate weight users, paper consistency modeling comments star ratings by mining associated comments, including interaction personalized characteristics combined sentiment analysis technology, then model. Second, double-layer group division mechanism considering regions time designed develop approach. Third, based on approach, developed. Finally, feasibility effectiveness proposed are verified through case for automobile comparative furnished. results application show that there significant difference between obtained arithmetic mean comprehensively considers division, which can be reflected weights process, also more decision results.