Social Computing / IEEE International Conference on Privacy, Security, Risk and Trust, 2010 IEEE International Conference on (2013)
Alexandria, VA, USA USA
Sept. 8, 2013 to Sept. 14, 2013
Social media has increasingly become an outlet for expression in society. Users of online social networks often associate with many other users who are all treated as "friends, " even if they do not have a strong connection, or what would be described as a friendship in real life. In this paper, we present an approach for predicting a user's closest friends on Facebook using machine learning techniques. We identify Facebook interactions that are most useful for predicting relationship strength and are able to predict a user's closest friends with up to 85% accuracy.
machine learning, social network analysis, tie strength, data mining
M. Madeira and A. Joshi, "Analyzing Close Friend Interactions in Social Media," 2013 International Conference on Social Computing (SocialCom)(SOCIALCOM), Alexandria, VA, USA, 2013, pp. 932-935.