Application Recommendation based on Metagraphs: Combining Behavioral and Published Information

Faced with so many mobile applications in the app store, users have difficulties finding their preferred mobile applications. Existing studies do not comprehensively consider implicit feedback in mobile applications and thus do not combine behavioral information and published information together to make recommendations. This paper proposes a novel method to recommend mobile applications based on metagraph embedding using the combination of behavioral information and published information. Specifically, this paper constructed a conceptual model using the combinations of behavioral information and published information that could well portray users and mobile applications. Based on this conceptual model, six metagraphs are designed to interpret the multidimensional relationships between users and mobile applications in the model. By random walking guided by each metagraph, a series of node sequences that could express node neighborhood are obtained. Finally, the similarity between users and apps is calculated using the embedded vector of each node, and the recommendations are given to the user. Based on a real-world dataset, we evaluate the performance of our method. The experimental result shows that our method outperforms existing models and methods in all metrics, in which the average F1-measure increases by 19.21%, and the average NDCG increases by 4.99%.