 |
Description
Recommender systems suggest information sources and products to users
based on learning from examples of their likes and dislikes. Most existing
recommender systems use collaborative filtering methods that base recommendations
on other users' preferences. By contrast, content-based methods use information
about an item itself to make suggestions. This approach has the advantage
of being able to recommended previously unrated items to users with unique
interests and to provide explanations for its recommendations. Our work
has focused on a content-based book recommending system called LIBRA.
Similar learning methods for categorizing text have numerous other applications
such as information filtering and automated classification of web pages.
We have also explored methods for exploiting properties of HTML in learning
for web-page classification.
|
|
