ARCHIVES

Understanding interest similarity in Online Social Networks (OSNs) is crucial for various applications. This study addresses the challenge of determining interest similarity on platforms like Facebook, where users may not explicitly disclose their interests. Utilizing a substantial dataset of 479,048 users and 5,263,351 user-generated interests, the research focuses on movies, music, and TV shows. Findings reveal homophily in interest similarity, demonstrating that individuals tend to share more similar tastes when they have comparable demographic information or are connected as friends. A practical prediction model is proposed, facilitating the selection of users with high-interest similarities and enhancing decision-making for OSN applications. Additionally, the paper introduces a novel method using a tag network to connect users with similar interests, outperforming traditional methods by providing a more efficient means of connecting like-minded individuals in social networks.