Neural Network Classification for user Profile Learning over Digital Library Recommendation Engine

Abstract

Objectives: To propose a hybrid recommendation engine to make perfect order of recommendations for online digital library portals. Methods/Statistical Analysis: The proposed model combines the content-based learning based upon the neutralized factors along with the collaborative learning for producing the recommendations on the basis of the interuser similarity, which is learned from the user’s profile representation vector. The hybrid recommendation algorithm is intended to produce more relevant recommendations for the digital library users. Findings: The proposed has been tested over the different sizes of the data. The proposed model has been designed for the discovery of the similar entities using the neural network classification and the top five entities are utilized for the calculation of the missing profile values to compute the recommendations over the digital library systems. The proposed model’s performance has been analyzed and studied using the statistical performance measuring parameters which elaborates the system performance from various perspectives. The experimental results have shows the robust performance of the proposed model in the terms of mentioned parameters. Application/Improvements: The proposed model has been improved the recommendations by the means of the calculating the inter user relevance to evaluate the recommendations for the user in the scope.