Associative Text Classification
Associative classification is a novel and powerful method originated from
the association rule mining. In the previous studies, a relatively small
number of high-quality association rules were used in the prediction. We
propose a new approach in which a large number of association rules are
generated. Then, the rules are filtered using a new method which is
equivalent to a deterministic Boosting algorithm. Through this equivalence,
our approach shows a good performance in the large-scale classification task
such as text categorization and biological sequence classification.
- Classification based on Boosting Association Rules
- Text Categrization
- Subcellular Localization Prediction of Proteins
- Input : Natural Language Documents (later, coverted to indexed
forms)
- Output : Multi-labeled prediction scores and Overall
performance
- Publications
- Yongwook Yoon, Gary Geunbae Lee. Text Categorization based on Boosting
Association Rules., Proceeding of the second Interantional Conference of
Semantic Computing (IEEE-ICSC 2008), pages 136-143.
- Yongwook Yoon, Gary Geunbae Lee. Efficient implementation of associative
classifiers for document classification. Information Processing and
Management: special issue on information retrieval research in Asia,
43(2):393-405, March 2007.