Analysis and Prospect of Recommendation System on social media

Abstract

Recommendation system works surprisingly well on providing interesting and informative contents to individual user by matching suitable information with target users, and it tremendously reduces the time users spend for searching relative contents while it is also cutting back the workload of content providers. There are two popular recommendation techniques: content-based and collaborative based filtering. The abilities of each technique is compared and analyzed, and how well they match the need of users on the social media platform. In addition, a typical form of hybrid recommendation that has the advantages of multiple techniques is also taken in the comparison. From the perspective of users in social media, each specific technique achieves some degree of success for the overall user satisfaction. Integrating techniques is a valuable attempt. This paper presents a look the origin and the development of recommender system in the past. The evolution of recommendation provides insight regarding what the future of recommender will become. The architecture of recommender system is also reviewed for understanding the way system performs. The key component inside the recommender architecture including matching, filtering, and objects utilized by technique which are critical factors in determination of prediction are examined. Different techniques used in filtering are analyzed for recognizing the advantages and the disadvantages for the purpose of social media. After all, the effectiveness of the hybrid recommendation technique on dealing with limitations of popular filtering is demonstrated.