Multiple sets of rules for text categorization

Authors:
Yaxin Bi;Terry Anderson;Sally McClean
Affiliations:
School of Computer Science, Queen's University of Belfast, Belfast, UK;Faculty of Engineering, University of Ulster, Newtownabbey, Co. Antrim, UK;Faculty of Engineering, University of Ulster, Newtownabbey, Co. Antrim, UK
Venue:
ADVIS'04 Proceedings of the Third international conference on Advances in Information Systems
Year:
2004

Citing 11
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Automated learning of decision rules for text categorization

ACM Transactions on Information Systems (TOIS)
A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Machine learning and data mining

Communications of the ACM
Sensor and Data Fusion Concepts and Applications

Sensor and Data Fusion Concepts and Applications
Information Retrieval

Information Retrieval
Text Categorization with Suport Vector Machines: Learning with Many Relevant Features

ECML '98 Proceedings of the 10th European Conference on Machine Learning
Lightweight Rule Induction

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Ensemble Methods in Machine Learning

MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Bagging, boosting, and C4.S

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper concerns how multiple sets of rules can be generated using a rough sets-based inductive learning method and how they can be combined for text categorization by using Dempster's rule of combination. We first propose a boosting-like technique for generating multiple sets of rules based on rough set theory, and then model outcomes inferred from rules as pieces of evidence. The various experiments have been carried out on 10 out of the 20-newsgroups – a benchmark data collection – individually and in combination. Our experimental results support the claim that “k experts may be better than any one if their individual judgements are appropriately combined”.