Context-Aware Application Prediction and Recommendation in Mobile Devices

In recent years, highly-functional mobile devices such as smart phones and car navigation systems are widely used. These are important for our daily life because we use their applications anywhere and anytime. With the variety of applications available on these devices, however, it becomes more difficult to choose an appropriate application. Therefore we need a mechanism that recommends us suitable applications, which should depend on a user's context because he/she uses his/her devices differently in every context. This paper shows that it follows a power law what applications a user executes in daily life, and proposes a novel approach to find context-aware applications in the mobile devices. This approach is based on the term frequency - inverse document frequency (TF-IDF), which is used for extracting important keywords in a document. Moreover, we propose an application recommendation mechanism using this approach. Experimental results show that this recommendation mechanism is more effective than the mechanism using Naive Bayes.