Support Vector Machine Text Classifier for Arabic Articles » książka
Support Vector Machine Text Classifier for Arabic Articles
ISBN-13: 9783639271416 / Angielski / Miękka / 2010 / 132 str.
In this book, we have implemented a support vector machine (SVM) text classifier for Arabic articles. Experimental results show that the SVM classifier outperformed Naive Bayesian (NB) and k-nearest neighbor (kNN) classifiers. We investigated the effectiveness of six state-of-the-art feature subset selection (FSS) methods, which are commonly used in text classification (TC) tasks, for our Arabic SVM text classification system. We implemented an Ant Colony Optimization Based-Feature Subset Selection (ACO Based-FSS) method for our Arabic SVM text classifier. The proposed FSS method adapted Chi-square statistic as heuristic information and the effectiveness of the SVM classifier as a guide to improving the selection of features for each category. Compared to the six state-of-the-art FSS methods, our ACO Based-FSS algorithm achieved better TC effectiveness. Evaluation used an in-house Arabic TC corpus that consists of 1445 documents independently classified into nine categories. The experimental results were presented in terms of macro-averaging precision, macro-averaging recall and macro-averaging F1 measures.
In this book, we have implemented a support vector machine (SVM) text classifier for Arabic articles. Experimental results show that the SVM classifier outperformed Naïve Bayesian (NB) and k-nearest neighbor (kNN) classifiers. We investigated the effectiveness of six state-of-the-art feature subset selection (FSS) methods, which are commonly used in text classification (TC) tasks, for our Arabic SVM text classification system. We implemented an Ant Colony Optimization Based-Feature Subset Selection (ACO Based-FSS) method for our Arabic SVM text classifier. The proposed FSS method adapted Chi-square statistic as heuristic information and the effectiveness of the SVM classifier as a guide to improving the selection of features for each category. Compared to the six state-of-the-art FSS methods, our ACO Based-FSS algorithm achieved better TC effectiveness. Evaluation used an in-house Arabic TC corpus that consists of 1445 documents independently classified into nine categories. The experimental results were presented in terms of macro-averaging precision, macro-averaging recall and macro-averaging F1 measures.
Czytaj nas na:
KrainaKsiazek.PL - Księgarnia Internetowa
