A heuristic approach to social network-based and context-aware mobile services recommendation

The rapid growth of the number of mobile services provides enormous potential for users to find mobile information of interest. How to use both social network analysis and contextual recommendation techniques to improve mobile services recommendation has received little notice. In this paper we introduce a new heuristic approach to search nearest neighbors for each mobile user based on both given contextual mobile user preferences and mobile social network relationships, and then predict unknown contextual mobile user preferences and finally generate contextual mobile recommendations. We evaluate it on a real-world data set and compare its performance with some classical baseline methods, showing improvements in terms of different evaluation metrics.