D. Dhinakaran,Dileep Kumar,S Dinesh,D. Selvaraj,K. Srikanth
标识
DOI:10.1109/mecon53876.2022.9751920
摘要
Recommender systems are becoming increasingly popular on the internet in recent years. The research has advanced by developing numerous iterations of personalized recommendation systems to increase suggestion effectiveness, use, and accessibility. Intelligence graph-based suggestions had already increasingly gained traction in industry and academia due to their ability to focusing on the following scarcity and performance problems. In this study, we present a novel approach that is based on a ranking-oriented personalized recommendation framework that autonomously suggests items of possible interest to viewers. To enhance predictions, the proposed method makes use of comparable author affiliations across articles. With an author-based search pattern, the system suggests papers to individual and special events to all scholars to help individuals gain more competence in their subject of interest. The approach does this by combining articles featuring comparable author affiliations and the author who appears the much more frequently. We demonstrate that the suggested algorithm performs better previous examine in the realm of research article recommendation.