Ranking Adaptation Svm for Target Domain Search

With the growth of different search engines, it becomes difficult for an user to search particular information effectively. If a search engine could provide domain specific information such as that confines only to a particular topicality, it is referred to as domain specific engine. Applying the ranking model trained for broad-based search to a domain specific search does not achieve good performance because of domain differences. Building a different ranking model for each domain is laborious and time consuming. In this paper, the ranking model used in broad-based search is adapted to domain specific search. An algorithm called Ranking Adaptation SVM is used to effectively adapt a ranking model to a target domain. Such an adaptation has advantages since it needs only the predictions from existing ranking models. Ranking Adaptability measurement is used to quantitatively estimate whether a ranking model can be adapted to new domain.