Influence of social communication on content-based recommendation

Abstract

One of basic divisions of information retrieval systems is content-based and collaborative filtering. Some hybrid methods exist combining both of them, but certain aspects still remain unexplored. In this paper we explore one: the influence of users communicating via social media on content-based recommendation systems. While in the system users do not know each other, outside they may make their own preferences known (e.g. tweeting recommendations), thus influencing the preferences of other users. Here we simulate several different types of such communication and its influence on content-based recommendation system. We intend to use this results for improving the quality of such systems.