Services for citizens provided by the government are often complex and related with various requirements. Citizens usually have a lot of queries regarding the E-governance services. The browsing history of the user is used to select the document of his or her interest along with the technique of semantic query expansion. Web mining methods are utilised to extract patterns of user access interests. The purpose of the study is to determine if patterns of user access interests can be extracted and to associate these patterns extracted, with other attributes to recommend information items that are likely to be of interest to the user. This enables the user to get better services. It can shorten the searching time, provides better services, and let users receive more suitable resources. Almost all the existing approaches for the recommender systems must rely on the usage history of users and focus on the current demands of the user. Therefore the items or pages which are added recently cannot be found. The reason being that, for these new items or pages, there are no accessed records, no ratings from users and no relationships are found by algorithm. In this paper a new framework is suggested which solves this problem. Here when a new item or page appears, its influence is also considered and based on this the new item or page will also be suggested to the user.Services for citizens provided by the government are often complex and related with various requirements. Citizens usually have a lot of queries regarding the E-governance services. The browsing history of the user is used to select the document of his or her interest along with the technique of semantic query expansion. Web mining methods are utilised to extract patterns of user access interests. The purpose of the study is to determine if patterns of user access interests can be extracted and to associate these patterns extracted, with other attributes to recommend information items that are likely to be of interest to the user. This enables the user to get better services. It can shorten the searching time, provides better services, and let users receive more suitable resources. Almost all the existing approaches for the recommender systems must rely on the usage history of users and focus on the current demands of the user. Therefore the items or pages which are added recently cannot be found. The reason being that, for these new items or pages, there are no accessed records, no ratings from users and no relationships are found by algorithm. In this paper a new framework is suggested which solves this problem. Here when a new item or page appears, its influence is also considered and based on this the new item or page will also be suggested to the user.
Keywords: Web usage mining, Web content mining, document retrieval, semantic query expansion.
