Focusing User Modeling For Age Specific Differences

Abstract When personalization and user satisfaction are the motives, demographic attributes play an important role. User’s demographic attributes or demographics include traits such as age, gender, race, occupation, political and religious views etc. There are differences in search and browsing behavior of a user based on these attributes. We have focused on these differences based on user’s age. The motivation to do so was to reduce the number of difficulties faced by users from different age groups, and to provide the most relevant result to the users query. In this paper, we offer a solution to this problem by showing how user age can be efficiently and accurately inferred based on their search query. Our approach uses Solr search engine in combination with the Bayesian classifier to predict the age of the user based on the query entered and the sequence of actions performed on the web.