Hybrid recommendation algorithm based on multi-attribute rating from online reviews

As the growing users and products in network shopping platform under the big data environment, the data sparsity and cold start problem are increasingly prominent which lead to the recommended effect of recommendation algorithm can't be satisfied by users. For this problem, the paper presents a construction method of user preference model and product feature model based on information mining of online reviews, and then it eases data sparsity through multi-attribute rating. And the paper solves the problem of user cold start and product cold start to a certain extent through the algorithm of similarity which is based user attributes and product attributes. Finally, the paper combines with multiple similarity algorithms to construct hybrid recommendation algorithm based on user preference and product feature. Simulation experiments verify the ability to solve the cold start problem and good recommendation accuracy of the algorithm through collecting 10000 online reviews information from the mobile channel of Amazon.