As the huge dimensionality of textual data restrains the classification accuracy, it is essential to apply feature selection (FS) methods as dimension reduction step in text classification (TC) domain. Most of the FS methods for TC contain several number of probabilities. In this study, we proposed a new FS method named as Extensive Feature Selector (EFS), which benefits from corpus-based and class-based probabilities in its calculations. The performance of EFS is compared with nine well-known FS methods, namely, Chi-Squared (CHI2), Class Discriminating Measure (CDM), Discriminative Power Measure (DPM), Odds Ratio (OR), Distinguishing Feature Selector (DFS), Comprehensively Measure Feature Selection (CMFS), Discriminative Feature Selection (DFSS), Normalised Difference Measure (NDM) and Max–Min Ratio (MMR) using Multinomial Naive Bayes (MNB), Support-Vector Machines (SVMs) and k-Nearest Neighbour (KNN) classifiers on four benchmark data sets. These data sets are Reuters-21578, 20-Newsgroup, Mini 20-Newsgroup and Polarity. The experiments were carried out for six different feature sizes which are 10, 30, 50, 100, 300 and 500. Experimental results show that the performance of EFS method is more successful than the other nine methods in most cases according to micro-F1 and macro-F1 scores.

Text classification (TC) is very important and critical task in the 21th century as there exist high volume of electronic data on the Internet. In TC, textual data are characterised by a huge number of highly sparse features/terms. A typical TC consists of many steps and one of the most important steps is undoubtedly feature selection (FS). In this study, we have comprehensively investigated the effects of various globalisation techniques on local feature selection (LFS) methods using datasets with different characteristics such as multi-class unbalanced (MCU), multi-class balanced (MCB), binary-class unbalanced (BCU) and binary-class balanced (BCB). The globalisation techniques used in this study are summation (SUM), weighted-sum (AVG), and maximum (MAX). To investigate the effect of globalisation techniques, we used three LFS methods named as Discriminative Feature Selection (DFSS), odds ratio (OR) and chi-square (CHI2). In the experiments, we have utilised four different benchmark datasets named as Reuters-21578, 20Newsgroup., Enron1, and Polarity in addition to Support Vector Machines (SVM) and Decision Tree (DT) classifiers. According to the experimental results, the most successful globalisation technique is AVG while all situations are taken into account. The experimental results indicate that DFSS method is more successful than OR and CHI2 methods on datasets with MCU and MCB characteristics. However, CHI2 method seems more accurate than OR and DFSS methods on datasets with BCU and BCB characteristics. Also, SVM classifier performed better than DT classifier in most cases.

Classification of medical documents was mostly carried out on English data sets and these studies were performed on hospital records rather than academic texts. The main reasons behind this situation are the lack of publicly available data sets and the tasks being costly and time-consuming. As the first contribution of this study, two data sets including Turkish and English counterparts of the same abstracts published in Turkish medical journals were constructed. Turkish is one of the widely used agglutinative languages worldwide and English is a good example of non-agglutinative languages. While English abstracts were obtained automatically from MEDLINE database with a computer program, Turkish counterparts of these documents were collected manually from the Internet. As the second contribution of this study, an extensive comparison on classification of abstracts obtained from Turkish medical journals was made by using these two equivalent data sets. Features were extracted from text documents with three different approaches: unigram, bigram and hybrid. Hybrid approach includes a combination of unigram and bigram features. In the experiments, three different feature selection methods and seven different classifiers were utilised. According to the results on both data sets, classification performance of the English abstracts outperformed the Turkish counterparts. Maximum accuracies were obtained from the combination of unigram features, distinguishing feature selector (DFS) and multinomial naïve Bayes (MNB) classifier for both data sets. Unigram features were generally more efficient than bigram and hybrid features. However, analysis of top-10 features indicated that nearly half of the features were translations of each other for Turkish and English data sets.