Abstract :

With The Exponential Growth Of Online News Content, Users Are Often Overwhelmed By The Vast Amount Of Information Available On Digital Platforms. Recommender Systems Play A Crucial Role In Delivering Personalized Content By Filtering And Suggesting Relevant News Articles Based On User Preferences. Traditional Recommendation Techniques Such As Collaborative Filtering And Content-based Filtering Face Limitations In Capturing Complex Relationships Between Users And News Items. This Project Proposes A Novel Approach For News Recommendation Using Graph Convolutional Neural Networks (GCNN), Which Effectively Model The Interactions Between Users, Articles, And Contextual Information. The Proposed System Represents Users And News Articles As Nodes In A Graph, Where Edges Denote Relationships Such As User Interactions, Reading History, And Content Similarity. Graph Convolutional Neural Networks Are Applied To Learn Node Embeddings By Aggregating Information From Neighboring Nodes, Enabling The Model To Capture Both Local And Global Structural Patterns. The System Utilizes Textual Features Of News Articles Along With User Behavior Data To Improve Recommendation Accuracy. Deep Learning Techniques Enhance The Model’s Ability To Learn Complex Patterns And Provide Personalized Recommendations. Experimental Results Demonstrate That The GCNN-based Approach Outperforms Traditional Methods In Terms Of Recommendation Accuracy And User Satisfaction. However, Challenges Such As Scalability And Dynamic Data Updates Remain. The Proposed System Provides An Efficient And Scalable Solution For Personalized News Recommendation, Improving User Engagement And Content Delivery In Modern Digital Platforms.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1913-1919

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite