A novel query expansion method based on predictive algorithms used for collaborative filtering was proposed. Query-document was considered as a measure to select the relevant document set and as an element of term weight calculation to improve retrieval performance. Collaborative filtering was used to predict the votes of a particular user from a database of user votes of other users. The object of predictive algorithms for collaborative filtering was to predict the values of empty elements of the active user.
|Number of pages||2|
|Journal||SIGIR Forum (ACM Special Interest Group on Information Retrieval)|
|Publication status||Published - 2001|
ASJC Scopus subject areas
- Management Information Systems
- Hardware and Architecture