Abstract
Mobile devices, including cell phones, capable of geo-positioning (or localization) are paving the way for new computer assisted systems called mobile location-based recommenders (MLBRs). MLBRs are systems that combine information on user’s location with information about user’s interests and requests to provide recommendations that are based on “location”. MLBR applications are numerous and emerging. One MLBR application is in advertisement where stores announce their coupons and users try to find the coupons of their interests nearby their locations through their cell phones. This chapter discusses the concept and characteristics of MLBRs and presents the architecture and components of a MLBR for advertisement.
TopAmong the various available MLBR applications, some are extensions of current mobile applications with the parameter of “location” as another way of injecting data into the decision process. (Yu & Chang, 2009) presented a personalized MLBR for tour planning. Sightseeing spots, hotels, restaurants, and other points of interest (POIs) to tourists are recommended based on tourist’s location, time, and personal preferences and needs. (Yang & Wang, 2009) developed an architecture using WEB2.0 services for restaurant recommender. In this research restaurants are recommended to users based on their location that is obtained via Global Positioning System (GPS). (Hinze & Buchanan, 2006) presented a MLBR for tourists called Trip Information Provider (TIP). TIP provides a user with general information based on their location, personal profile, and their travel history once they have entered a museum. Moreover, users are informed of scheduled events such as opening hours of a museum. (Rashid, Coulton, & Edwards, 2008) presented a system which provides location-based information/advertisement for mobile users. By implementing the system in a supermarket, nearby customers are provided with the latest information on products as well as special offers, using Bluetooth. SMMART (Kurkovsky & Harihar, 2005) is another context-aware system which provides users with recommendations or promotions in a given retail store, considering user’s preferences. (Bellotti, et al., 2008) presented Magitti, a leisure guide, which automatically recommends its user a leisure activity. It predicts user’s future activity based on context and their patterns of behavior, and then recommends a useful activity considering user’s preferences. (Park, Hong, & Cho, 2007) developed a map-based personalized recommendation system, which collects context information, location, time, weather upon a mobile user request, and provides the user with a proper service on a map. The POI recommender presented by (Horozov, Narasimhan, & Vasudevan, 2006) is another mobile recommender which provides its users with recommendations on POIs (e.g., restaurant) considering their location and preferences.
Key Terms in this Chapter
Mobile Computing: Refers to the development on and utilization of mobile devices.
Location-Based Social Networking (LBSN): A LBS for Social Networking (SN) in that members of the network share information based on their current location with one another.
Recommender: Any system that provides recommendation based upon user’s preferences.
Location-Based Services (LBSs): Prepare location-centric information and deliver information to user’s current location. Geo-positioning sensors, to determine user’s current location, and wireless communications, to deliver information, are the most important components of LBSs.
M-commerce: Refers to the process of conducting commerce through wireless communications and mobile devices.
Mobile Location-Based Recommender (MLBR): A recommender that provides location-centric recommendation and delivers recommendation to user’s current location.
Navigation: The process of moving from one location to another.