A method for ranking products based on LDA topic model and stochastic dominance

Abstract

It is difficult for consumers to make purchase decisions based on massive amount of online reviews. Therefore, a product selection method based on LDA topic model and stochastic dominance rules is proposed. The method first uses the LDA topic model to extract product attributes; secondly, sentiment analysis is applied to calculate the probability distribution and expectation matrix of different sentiment orientation; further, stochastic dominance rules and PROMETHEE-Ⅱ are used to calculate the ranking value of each product with different product attributes; finally, the best product is selected through the overall ranking value calculated by the entropy method. The feasibility and practicability of the method are illustrated by an example.