Title | ||
---|---|---|
A Hybrid Approach to Error Reduction of Support Vector Machines in Document Classification |
Abstract | ||
---|---|---|
In this paper, we present a hybrid method of support vector machine and k-nearest neighbor to improve the performance of automatic text classification. The proposed methods first classify a given document using SVM which shows the best performance in text classification, and then is reinforced by k-NN for the documents that are not confidently classified by SVM. According to the experimental results, the hybrid method achieves the F-score of 85.2, which implies that the hybrid method outperforms SVM alone |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ITNG.2006.10 | ITNG |
Keywords | Field | DocType |
hybrid method,automatic text classifcation,hybrid approach,pattern classification,document classification,text classification,vector machine,k-nearest neighbor,best performance,hybrid method fo support,automatic text classification,text analysis,support vector machines,error reduction,k nearest neighbor,support vector machine,information technology | k-nearest neighbors algorithm,Document classification,Structured support vector machine,Text mining,Least squares support vector machine,Pattern recognition,Computer science,Support vector machine,Artificial intelligence,Relevance vector machine,Linear classifier,Machine learning | Conference |
ISBN | Citations | PageRank |
0-7695-2497-4 | 0 | 0.34 |
References | Authors | |
5 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yoon-Shik Tae | 1 | 6 | 1.52 |
Jeong Woo Son | 2 | 2 | 1.84 |
Mi-hwa Kong | 3 | 0 | 0.68 |
Jun-Seok Lee | 4 | 25 | 5.25 |
Seong-Bae Park | 5 | 311 | 47.31 |
Sangjo Lee | 6 | 110 | 19.15 |