Can Smartphone Co-locations Detect Friendship? It Depends How You Model It
arXiv:2008.02919
Abstract
We present a study to detect friendship, its strength, and its change from smartphone location data collectedamong members of a fraternity. We extract a rich set of co-location features and build classifiers that detectfriendships and close friendship at 30% above a random baseline. We design cross-validation schema to testour model performance in specific application settings, finding it robust to seeing new dyads and to temporalvariance.
References in corpus (7)
- Dynamics of person-to-person interactions from distributed RFID sensor networks
- What's in a crowd? Analysis of face-to-face behavioral networks
- High resolution dynamical mapping of social interactions with active RFID
- Measuring large-scale social networks with high resolution
- Geographic constraints on social network groups
- The Strength of Friendship Ties in Proximity Sensor Data
- Comparison of Cross-Validation Methods for Stochastic Block Models