LAUSR

Check-in facility in a location-based social network (LBSN) enables people to share location information as well as real-life activities. Analysing these historical series of check-ins to predict the future locations to be visited has been very popular in the research community. However, it has been found that people do not intend to share the privately visited locations and activities in a LBSN. Research into extrapolating unchecked locations from historical data is limited. Knowledge of hidden locations can have a wide range of benefits to society. It may help the investigating agencies in identifying possible places visited by a suspect, a marketing company in selecting potential customers for targeted marketing, for medical representatives in identifying areas for disease prevention and containment, etc. In this paper, we propose an Associative Location Prediction Model (ALPM), which infers privately visited unchecked locations from a published user trajectory. The proposed ALPM explores the association between a user’s checked-in data, the Hidden Markov Model and proximal locations around a published check-in for predicting the unchecked or hidden locations. We evaluate ALPM on real-world Gowalla LBSN dataset for the users residing in Beijing, China. Experimental results show that the proposed model outperforms the existing state-of-the-art work in the literature.