A Novel Paper Recommendation Method Empowered by Knowledge Graph: for Research Beginners
This addresses the problem of inefficient paper discovery for research beginners, but it appears incremental as it builds on existing knowledge graph methods for recommendation.
The paper tackles the inefficiency of traditional paper search methods for research beginners in cross-domain scenarios by proposing a novel recommendation method using 'master-slave' domain knowledge graphs, which demonstrated feasibility in experiments across two cross-domains and three academic databases.
Searching for papers from different academic databases is the most commonly used method by research beginners to obtain cross-domain technical solutions. However, it is usually inefficient and sometimes even useless because traditional search methods neither consider knowledge heterogeneity in different domains nor build the bottom layer of search, including but not limited to the characteristic description text of target solutions and solutions to be excluded. To alleviate this problem, a novel paper recommendation method is proposed herein by introducing "master-slave" domain knowledge graphs, which not only help users express their requirements more accurately but also helps the recommendation system better express knowledge. Specifically, it is not restricted by the cold start problem and is a challenge-oriented method. To identify the rationality and usefulness of the proposed method, we selected two cross-domains and three different academic databases for verification. The experimental results demonstrate the feasibility of obtaining new technical papers in the cross-domain scenario by research beginners using the proposed method. Further, a new research paradigm for research beginners in the early stages is proposed herein.