Recommending Location Privacy Preferences in Ubiquitous Computing

Location-Based Services have become increasingly popular due to the prevalence of smart devices. The protection of users’ location privacy in such systems is a vital issue. Conventional privacy protection methods such as manually predefining privacy rules or asking users to make decisions every time they enter a new location may not be usable, and so researchers have explored the use of
machine learning to predict preferences. Model-based machine learning
classifiers which are used for prediction may be too computationally complex to be used in real-world applications. We propose a location-privacy recommender that can provide users with recommendations of appropriate location privacy settings through user-user collaborative filtering. We test our scheme on real world dataset and the experiment results show that the performance of our scheme is close to the best performance of model-based classifiers and it outperforms model-based classifiers when there are no sufficient training data.