Comparative study of Content based and Collaborative Filtering Recommendation Systems for Social Media
Kushal Sharma, Sarita Patil
Department of Computer Engineering , Raisoni College of Engineering and Management
kushalsharma76@gmail.com
sarita.patil@raisoni.net
Abstract - Recommendation systems are widely used in social media to help users discover motivational content that they might find interesting. There are two main types of recommendation systems: content-based and collaborative-based. In this research paper, we compare these two approaches for a Motivational Content-based Recommendation System for Social Media. We found that content-based recommendation systems outperform collaborative-based systems in terms of accuracy and efficiency. However, collaborative-based systems offer better diversity and serendipity in the recommended content. We conclude that a hybrid approach that combines both methods could provide the best results. Social media is becoming a necessity in today’s era. It is essential to our daily lives. Nobody is able to escape its influence. People spend 70% of their time on social media watching movies, chatting, conversation, online gaming. It’s always been interesting to know the impact of it over the young generation of India. The increasing popularity of social media resources such as blogs, bookmarks, chat rooms, forums and video portals in recent years has attracted diverse users. The increasing popularity of the Internet has resulted in an abundance of online content, which prompted the development of recommendation systems on social media. As a result, since the year 2000, there has been a considerable increase in study on the dynamic growth of recommendation systems in social media. In order to find the most relevant recommendations, social media recommendation systems (SMRS) use a variety of recommendation fields, including item, user, location, tag, event, tour, and game. The purpose of this research paper is to show motivational based recommendations to youth on social media.
Keywords - Recommender system , Social media , Hybrid Filtering , Motivational based , Social recommender system ,Content-based Recommendation , Collaborative-based Recommendation
