Research Paper Recommendation Based on the Knowledge Gap

The massively growing of literature resource makes it a challenge for researchers to find useful papers. To solve the information overload problem, some researches on personalized paper recommendation have been conducted. However, the knowledge gap between a researcher´s background knowledge and research target is seldom concerned. In this paper, we propose a knowledge-gap based literature recommendation method to support researchers to fulfill literature support. Firstly, domain knowledge is modeled with the concept map, based on which background knowledge and target knowledge are analyzed. Then, knowledge gap is defined both graphically and intuitively with the knowledge map. To bridge the knowledge gap, we design a graph-based method to explore some suitable knowledge paths, which can help a researcher to learn the requisite knowledge in accordance with cognition pattern. Finally, experiments are performed to demonstrate the effectiveness of the proposed method.