A novel semi-naive Bayesian restaurant recommendation method considering feature correlation

This paper introduces a novel recommendation model, namely, the maximum feature dependency semi-naive Bayesian (MDN) model, which is aimed at addressing feature correlation in restaurant selection. Existing restaurant recommendation methods ignore feature correlation and negative samples to improve recommendation accuracy. In contrast, the proposed recommendation model establishes maximum dependency features for each attribute, using both positive and negative samples to enhance its accuracy. The model first performs logarithmic division transformation on naive Bayesian classification to obtain user behavior patterns that can be sorted. Then, it combines frequent pattern mining to optimize user behavior patterns and obtain a semi-naive Bayesian recommendation model for restaurant recommendations. Experiments on a Yelp dataset show that the restaurant recommendation algorithm based on naive Bayesian user behavior patterns outperforms other basic recommendation methods. The proposed recommendation model stably improves recommendation methods based on naive Bayesian user behavior patterns, whereas other semi-naive Bayesian methods reduce accuracy due to the consideration of feature correlation. The restaurant recommendation method based on user behavior patterns also improves the interpretability of restaurant recommendations.