Publisher

IAESCOREIAESCORE

Journal International Journal of Electrical and Computer Engineering (IJECE)International Journal of Electrical and Computer Engineering (IJECE) Abstract

Recommendation systems are gaining great importance with e-Learning and multimedia on the internet. It fails in some situations such as new-user profile (cold-start) issue. To overcome this issue, we propose a novel goal-based hybrid approach for user-to-user personalized similarity recommendation and present its performance accuracy. This work also helps to improve collaborative filtering using k-nearest neighbor as neighborhood collaborative filtering (NCF) and content-based filtering as content-based collaborative filtering (CBCF). The purpose of combining k-nn with recommendation approaches is to increase the relevant recommendation accuracy and decrease the new-user profile (cold-start) issue. The proposed goal-based approach associated with nearest neighbors, compare personalized profile preferences and get the similarities between users. The paper discussed research architecture, working of proposed goal-based approach, its experimental steps and initial results.

Conclusion

This paper introduced an efficient hybrid approach for recommender systems.The proposed goal-based recommendation approach used content-based and collaborative filtering with machine learning technique (k-nn).Experimental results show that the user-to-user personalized recommendation can improve the recommendation accuracy of e-learning recommender systems in terms of the new-user profile (cold-start) issue.

Future Research

Future research should focus on improving the novel goal-based hybrid approach and increasing the experimental data to test its efficiency with larger datasets. Further investigation could explore the integration of more advanced machine learning techniques to enhance the accuracy and scalability of the recommendation system. Additionally, exploring the incorporation of user feedback mechanisms and dynamic profiling could personalize recommendations more effectively and address evolving user preferences. These advancements will contribute to building more robust and user-centric recommender systems capable of overcoming the limitations of traditional approaches and providing more relevant and satisfying experiences for users in e-learning and multimedia environments.

Metadata

File size	194.84 KB
Pages	8
DMCA	Report