To provide assistance with tasks such as retrieving USENET news articles or identifying interesting Web pages, an intelligent agent requires information about a user’s interests and needs. Machine learning techniques are now being used to acquire this information. A general architecture is presented, and two approaches to learning through observation are described. An instantiation of the architecture is then evaluated.
|Title of host publication||Proceedings of AAAI 1996 Stanford Spring Symposium on Machine Learning in Information Access|
|Editors||Marti A Hearst, Haym Hirsh|
|Place of Publication||Menlo Park, CA|
|Publication status||Published - 1996|
- user agents
- user profiling
- machine learning