SCAN Intent

Mining a user search context promises major improvements in several key aspects of Web search. Usage information such as search click-through has been a valuable source of information to determine the user search needs. However, such server side information is limited to query and corresponding clicks. Such query logs often do not contain sufficient information to understand user search needs. Therefore, it is important to capture the user other activities, such as documents read or URLs opened before submitting a search query. To capture the user activities, the proposed new framework, SCAN, which is easy to install and use, yet powerful to capture all the user activities, is an effective tool. The problems with current existing methods are they don't provide authority and transparency on data they collect from the user desktop. Our new proposed framework provides both authority and transparency to user. Using our software, research groups can create their own Desktop dataset for evaluation of new techniques. The SCAN framework collects information about a user client side activities (for both Desktop and Web).