A Hybrid Book Recommendation Algorithm Based on Context Awareness and Social Network
Huayong Liu, Nianlai Jiao · 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · 2020
The resources of university libraries are constantly enriched, and the needs of users are increasingly diversified and personalized. It is difficult to find the resources they want in time. To solve this problem, this paper proposes a hybrid book recommendation algorithm based on context awareness and social network. The algorithm firstly obtains the user's current task and context information, and then calculates the context entropy and context weight to represent the influence degree of different context factors on resource selection. Traditional Pearson similarity is combined with the similarity calculated by the neighborhood-based social network layer to get the hybrid user similarity. The final prediction results are obtained by the hybrid weighting process of the users' prediction scores in different context. Finally, the algorithm is tested by experiments. The results show that the proposed algorithm outperforms traditional collaborative filtering algorithm in precision and recall rate.