Academic Recommendation on Graph with Dynamic Transfer Chain

Academic contents update and learner´s capability change over time. But nowadays, academic recommendation system does not take time factors into account. There are two challenges to capture learner´s preferences and learning context accurately and dynamically. First modeling academic trend and user´s cognitive level transferred by time is a hard problem. And designing dynamic algorithm to improve recommendation accuracy with implicit behavior data is difficult. In this paper, we propose Dynamic Transfer Chain (DTC) to model user´s preferences and academic context over time on transaction data. Based on DTC model, we present a novel algorithm Dynamic Academic Recommendation on Graph (DARG). We evaluate the effectiveness of our method using an open dataset named CiteULike, including 9170 users, 11343 papers, 194596 user-paper pairs. The evaluation metric we used is Hit Ratio. The results show that our proposed approach gives 12.873% to 33.852% improvement over the previous counterpart, including User-KNN, Item-KNN, TUser-KNN, TItem-KNN.