A Survey on Enhancing Scientific Article Recommendation using Citation Relationships and Graph Learning

Scientific research article are growing rapidly in day today life. So it is more difficult to analyze the huge volume of big scholarly data for finding relevant research paper, relevant publication avenue, etc it is leads to information overload problem. Thus this problem is overcome by recommender system. In an existing system, proposed propose a novel recommendation method which incorporates information on common author relations between articles. It used only two features which are defined based on information about pair wise articles with common author relations and commonly appeared authors, to determine target researchers for recommendation. In our proposed system we add more additional features such as author impact, author reference, topic similarity and citing topic entropy, reference count, publication age and citing terms to improve the resolution of target researchers for recommendation. The experimental results will prove the effectiveness of proposed technique with additional features for scientific article recommender system.