Bluetooth pooling to enrich co-presence information

Bluetooth has become a widely used source of co-presence information to determine a user’s social context. However using Bluetooth in this way has several technological limi-tations including sensing time and effective range. This paper describes the technique of “Bluetooth pooling” which aggregates Bluetooth metadata collected from multiple users and propagates it among proximal users to create a more accurate record of co-presence. We also present the results of applying the Bluetooth pooling technique to a real world dataset of cameraphone photos annotated with Bluetooth co-presence metadata collected from over 65 users over 7 months