A Framework for Reviewer Recommendation Based on Knowledge Graph and Rules Matching
Yaoguang Yong, Yao Zheng, Yawei Zhao · 2021
With the increasing number of academic researchers, a wide range of papers are produced. As such, reviewer assignment stands out in ensuring the high quality of academic research. However, manual reviewer assignment faces a great difficulty due to the vast diversity of research topics. The complexity of these research topics also adds to the difficulty in reviewer-paper match. To solve these problems, we design a reviewer assignment system based on knowledge graph and rules matching. This design first extracts the keywords of the papers with a hierarchical semantic representation. Then, the rule engine is established by means of the knowledge graph and rules matching in order to reach a fast recommendation process. This design improves the efficiency and the correctness of the reviewer assignment process and provides sufficient interpretability for the recommended results.