Intelligent e-government services with personalized recommendation techniques

Information overload is becoming one of the problems that hinder the effectiveness of e-government services. Intelligent e-government services with personalized recommendation techniques can provide a solution for this problem. Existing recommendation approaches have not entirely considered the influences of attributes of various online services and may result in no guarantee of recommendation accuracy. This study proposes a new approach to handle recommendation issues of one-and-only items in e-government services. The proposed approach integrates the techniques of semantic similarity and the traditional item-based collaborative filtering. A recommender system named Smart Trade Exhibition Finder has been developed to implement the proposed recommendation approach. The recommender system can be applied in e-government services to improve the quality of government-to-business online services.