Rank distance aggregation as a fixed classifier combining rule for text categorization

Authors:
Liviu P. Dinu;Andrei Rusu
Affiliations:
Faculty of Mathematics and Computer Science, University of Bucharest, Bucharest, Romania;Faculty of Mathematics and Computer Science, University of Bucharest, Bucharest, Romania
Venue:
CICLing'10 Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing
Year:
2010

Citing 5
Cited 0

Experiments with Classifier Combining Rules

MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
On the classification and aggregation of hierarchies with different constitutive elements

Fundamenta Informaticae
An efficient approach for the rank aggregation problem

Theoretical Computer Science
A Generalization of the Assignment Problem, and its Application to the Rank Aggregation Problem

Fundamenta Informaticae
A Multi-Criteria Decision Method Based on Rank Distance

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we show that Rank Distance Aggregation can improve ensemble classifier precision in the classical text categorization task by presenting a series of experiments done on a 20 class newsgroup corpus, with a single correct class per document. We aggregate four established document classification methods (TF-IDF, Probabilistic Indexing, Naive Bayes and KNN) in different training scenarios, and compare these results to widely used fixed combining rules such as Voting, Min, Max, Sum, Product and Median.