Asking Images: Hybrid Recommendation System for Tourist Spots by Hierarchical Sampling Statistics and Multimodal Visual Bayesian Personalized Ranking

“Data sparseness” is a key issue in current research works on recommendation systems. However, additional information, such as texts, images, knowledge graph, and audios, that is correlated to items helps alleviate the problem to some extent. We focus our research on designing a novel hybrid recommendation system for tourist spots. Tourist spot images are utilized to suppress the “data sparseness” problem in the recommendation procedure. First, a novel multimodal visual bayesian personalized ranking algorithm is proposed to fully utilize the cross-modal semantic correlations among different image features. Then, a new recommendation list called
$L_{\mathrm {A}}$
is generated accordingly from the multimodal perspective. Second, user preference is acquired using the hierarchical sampling statistics model. A new recommendation list called
$L_{\mathrm {H}}$
is generated in turn from the statistical perspective. Finally, hybrid recommendation results are obtained on the basis of
$L_{\mathrm {H}}$
and
$L_{\mathrm {A}}$
. Experimental results demonstrate that the proposed hybrid recommendation system for tourist spots is effective and robust. It is superior to other competitive baselines. More importantly, the proposed hybrid recommendation system is good at recommending a group of tourist spots and more stable than baselines, indicating its high practical value.