Scholarly Article Recommendation System for Enhanced Research Insights

Recommendation systems have recently received a growing amount of attention, especially academic article recommendation systems in data mining area. Using both data mining algorithms and collaborative filters to process this information, compare the user’s likes against the content of the articles themselves. Proposed approach employs collaborative filtering, content-based filtering and CHARM sequential pattern mining to stage personalized recommendations. By analysing user behaviours, the contents of the suggested articles, citation networks between papers, and other different features on reading orders, improves the accuracy and relevance of suggestions. Various metrics are used to assess the performance of your recommendations, such as precision, recall, and diversity. This paper focuses on the browsing and downloading history as well as to improve recommendation accuracy by refining user profiles and behavior.