Design of Large Data Evaluation Model for Optimal Tourist Attractions

Abstract

It is of great importance to recommend the optimal tourist attractions through big data analysis. Therefore, in this paper we introduce the LDA topic model to recommend tourist attractions for travelers. The LDA model refers to a three layer hierarchical Bayesian model, in which each element of a collection is represented as a finite mixture on underlying topics. Afterwards, the weight of user vector is calculated by a TF-IDF policy where the TF is word frequency in user's profile and IDF is the number of users who have focused on a particular tourist attraction. Furthermore, a user is represented by a vector, in which each dimension is a latent topic of LDA. Next, the proposed personalized tourist attraction recommendation algorithm is given. Experimental results demonstrate that the proposed can effectively find optimal tourist attractions for users.