Scientific American writes:
If search engines could take the broader task context of a person’s query into account–that is, a user’s recent search subjects, personal behavior, work topics, and so forth–their utility would be greatly augmented. Determining user context will require software designers to surmount serious engineering hurdles, however. Developers must first build systems that monitor a user’s interests and habits automatically so that search engines can ascertain the context in which a person is conducting a search for information, the type of computing platform a user is running, and his or her general pattern of use. With these points established beforehand and placed in what is called a user profile, the software could then deliver appropriately customized information. Acquiring and maintaining accurate information about users may prove difficult. After all, most people are unlikely to put up with the bother of entering personal data other than that required for their standard search activities.
Another class of context-aware search systems would take into account a person’s location. If a vacationer, for example, is carrying a PDA that can receive and interpret signals from the Global Positioning System (GPS) or using a radio-frequency technique to establish and continuously update position, systems could take advantage of that capability. One example of such a technology is being developed by researchers at the University of Maryland. Called Rover, it is a system that makes use of text, audio or video services across a wide geographic area. Rover can present maps of the region in a user’s vicinity that highlight appropriate points of interest. It is able to identify these spots automatically by applying various subject-specific ” filters” to the map.