Social-Based Recommender Systems
Online social networks, such as Facebook, provide a wealth of information that we can leverage for recommending a variety of artifacts, such as news articles, movies, books, etc. While recommender systems have been extensively researched since the mid-1990s, the study of social-based recommender systems is a new area. One key insight is that social-based recommendations should account for a number of dimensions within a user’s social network, including social relationship strength, expertise, and user similarity. We seek to develop novel ensemble recommender systems that leverage these dimensions. Our research intersects with a number of domains in computer science, including data mining, machine learning, information retrieval, human-computer interaction, and distributed systems.
Mike Gartrell, Xinyu Xing, Qin Lv, Aaron Beach, Richard Han, Shivakant Mishra, Karim Seada, “Enhancing Group Recommendation by Incorporating Social Relationship Interactions”, Proceedings of the 16th ACM International Conference on Supporting Group Work (GROUP) 2010, pp. 97-106, doi: 10.1145/1880071.1880087.