Content-Based Filtering for Personalized Article Recommendations System

Abstract

This research investigates the development and evaluation of an article recommendation system, based on content-based filtering. The system utilizes natural language processing techniques to extract meaningful features from article text, such as keywords. These features are then used to calculate similarity between articles, enabling the system to recommend articles with similar content to users based on their reading history. The performance of the Content-Based Filtering Algorithm is assessed by evaluating its effectiveness in providing relevant and personalized article recommendations to users. For instance, the model successfully identified "Google shares data center security and design..." as the most similar article to the query "Google Data Center 360° Tour" based on the lowest Euclidean distance (1.18).