By clicking “Check Writers’ Offers”, you agree to our terms of service and privacy policy. We’ll occasionally send you promo and account related email
No need to pay just yet!
About this sample
About this sample
Words: 1223 |
Pages: 3|
7 min read
Published: Nov 8, 2019
Words: 1223|Pages: 3|7 min read
Published: Nov 8, 2019
The progressive information technologies which have resulted from the evolution of Location-Based Services (LBSs) have hugely enhanced people’s urban lives. Location-Based Social Networks (LBSNs) provide users platforms to check-in and share their current locations, thoughts, experiences and reviews about Point-of-Interest (POI) with their anyone. These huge amount of heterogeneous data in LBSNs enabled the development on POI recommendation. It has attracted much effort in research community to develop accurate POI recommender systems in various scenarios such as mobile, automotive and business applications. As our focus is on automotive scenarios and in recent automotive modern driver information systems, there is a large volume of data available to the driver such as digital broadcasting information, global positioning system(GPS) information and in vehicle application information. If all these data are given unprocessed to the driver, information overload becomes a significant issue. As such, POI recommendation service is highly suitable to mobility application.
For example, it can decrease the risk from traffic accidents by avoiding inputting long location name when users search for places to go. Hence, it not only useful users to discover new locations easily, but also helps users to obtain relevant POIs without wasting a lot of time on searching, especially when they are in a new area. In past research, common problems faced in POI recommendation systems are cold start and data sparsity. Cold start problem is caused by limited activity history of users and locations in the system as for a new user or location, the recommendation model does not have sufficient information to give useful recommendations. Due to the rapid growth of new users on LBSNs, the problem gets even worse. Similarly, data sparsity is due to the total data in the recommendation model is not enough for processing and recognizing related users/items. Therefore, some hybrid approaches and novel methods that consider the different kinds of recommendation models are required.
Browse our vast selection of original essay samples, each expertly formatted and styled