Abstract
To classify vast unknown documents on the web according to each user's view, FOCUS (the Fuzzy dOCUment ordering System) is developed based on fuzzy document selection, fuzzy document matching, and semantic concept extraction. The FOCUS can flexibly order vast unknown documents with respect to each user's preference that is obtained by learning based on few training data. An experiment using 60 documents (20 training data and 40 unknown documents) extracted from the Internet Movie Data Base (IMDB), is performed for 5 examinees. It is confirmed that the FOCUS achieves sufficient results (precision rate 60 %).
Original language | English |
---|---|
Pages (from-to) | 11-19 |
Number of pages | 9 |
Journal | International Journal of Fuzzy Systems |
Volume | 7 |
Issue number | 1 |
Publication status | Published - Mar 2005 |
Externally published | Yes |
Keywords
- Concept Extraction
- Document Retrieval
- Fuzzy Sets
- Vector Space Model