Quercia, D.; Capra, L.; (2009) FriendSensing: recommending friends using mobile phones. In: RecSys' 09: Proceedings of the third ACM conference on Recommender systems. (pp. pp. 273-276). Association for Computing Machinery: New York, US.

Preview

PDF 16835.pdf Download (299kB)

Abstract

Social-networking sites, such as Facebook, require members to manually find and confirm their friends. Finding friends is tedious for some and may be made less so by automating the process. We propose to do so by means of a framework that we call FriendSensing. Using short-range technologies (e.g., Bluetooth) on their mobile phones, social-networking users “sense” and keep track of other phones in their proximity. Proximity records are then processed using a variety of algorithms that are based on social network theories of geographical proximity and of link prediction. This processing can be performed either on the social-networking website, after records have been uploaded, or locally on the user’s mobile phone, so that privacy-conscious individuals do not have to disclose their proximity data to the social networking website. The result is a personalized and automatically generated list of people the user may know. We evaluate the extent to which FriendSensing helps users find people they know, and we do so against real mobility and social network data.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item