Recipient suggestion for electronic messages using local social network data.
Authors
Abstract
Social network users often want to send a message to a group of recipients. An algorithm that recommends other possible recipients given an initial set of recipients is introduced in this paper. The algorithm uses different types of local user data: profile, friendship graph, posts, and social interactions (likes, comments, tags). Experimental evaluation using Facebook application demonstrated that the algorithm is able to make suggestions meaningful to experts.
Full text of the paper in pdfEdition
Proceedings of SYRCoDIS'14: The Tenth Spring Researchers Colloquium on Databases and Information Systems, Velikiy Novgorod, 2014.
Research Group
All publications during 2014
