Feature reduction techniques for Arabic text categorization

Journal of the American Society For Information Science and Technology, 2006

In this article we propose a distance-based classifier for categorizing Arabic text. Each category is represented as a vector of words in an m-dimensional space, and documents are classified on the basis of their closeness to feature vectors of categories. The classifier, in its learning phase, scans the set of training documents to extract features of categories that capture inherent categoryspecific properties; in its testing phase the classifier uses previously determined category-specific features to categorize unclassified documents. Stemming was used to reduce the dimensionality of feature vectors of documents. The accuracy of the classifier was tested by carrying out several categorization tasks on an in-house collected Arabic corpus. The results show that the proposed classifier is very accurate and robust.

Journal of Information Science, 2014

Text Categorisation or Classification (TC) is concerned with placing text documents in their proper category according to their contents. Due to the various applications of TC and the large volume of text documents uploaded on the Internet daily, the need for such an automated method stems from the difficulty and tedium of doing such a process manually. The usefulness of TC is manifested in different fields and needs. For instance, the ability of automatically classifying an article or an email into its right class (Arts, Economics, Politics, Sports, etc.) would be very appreciated by individual users as well as companies. This paper is concerned with TC of Arabic articles. It contains a comparison of the five best known algorithms for TC. It also studies the effects of utilizing different Arabic stemmers (light and root-based stemmers) on the effectiveness of these classifiers. Furthermore, a comparison between different data mining software tools (Weka and RapidMiner) is presented. The results illustrate the strong accuracy provided by the SVM classifier, especially when used with the light10 stemmer. This outcome can be used in future as a baseline to compare with other unexplored classifiers and Arabic stemmers.

International Journal of Data Mining & Knowledge Management Process, 2013

Text pre-processing of Arabic Language is a challenge and crucial stage in Text Categorization (TC) particularly and Text Mining (TM) generally. Stemming algorithms can be employed in Arabic text preprocessing to reduces words to their stems/or root. Arabic stemming algorithms can be ranked, according to three category, as root-based approach (ex. Khoja); stem-based approach (ex. Larkey); and statistical approach (ex. N-Garm). However, no stemming of this language is perfect: The existing stemmers have a small efficiency. In this paper, in order to improve the accuracy of stemming and therefore the accuracy of our proposed TC system, an efficient hybrid method is proposed for stemming Arabic text. The effectiveness of the aforementioned four methods was evaluated and compared in term of the F-measure of the Naïve Bayesian classifier and the Support Vector Machine classifier used in our TC system. The proposed stemming algorithm was found to supersede the other stemming ones: The obtained results illustrate that using the proposed stemmer enhances greatly the performance of Arabic Text Categorization.

This paper compares a few statistical feature selection techniques for Arabic text. Feature selection is especially important for text classification because, when dealing with text, the number of features/words increases rapidly. This makes the document-term matrix a sparse one which affects the performance of classifiers in terms of accuracy and in terms of processing time. One opts to reduce the number of features during preprocessing by eliminating stopwords, or stemming. This paper adds one step to preprocessing by reducing the number of features based on their merit as determined by some statistical measures such as correlation, Chi square, deviation, and uncertainty. The dataset that was used in this study consists of 4,000 Arabic documents that fall into two categories. Naïve Bayes with 3-fold cross validation is used in this study. Results show that weight by correlation gave very high accuracy with very little time. Still, the highest accuracy was achieved in the base case, when no filters were used, but it took the classifier twice the time required with weight by correlation.

International Journal of Advanced Computer Science and Applications

The world has witnessed an information explosion in the past two decades. Electronic devices are now available in many varieties such as PCs, Laptops, book readers, mobile devices and with relatively affordable prices. This and the ubiquitous use of software applications such as social media and cloud applications, and the increasing trend towards digitalization, the amount of information on the global cloud has surged to an unprecedented level. Therefore, a dire need exists in order to mine this massively large amount of data and produce meaningful information. Text Classification is one of the known and well established data mining techniques that has been used and reported in the literature. Text classification methods include statistical and machine learning algorithms such as Naive Baysian, Support Vector Machines and others have widely been used. Many works have been reported regarding text classification of various languages including English, Chinese, Russian, and many others. Arabic is the fifth most spoken language in the world. There has been many works in the literature for Arabic text classification. However, and to the best of our knowledge, there is no recent work that presents a good, critical and comprehensive survey of the Arabic text classification for the past two decades. The aim of this paper is to present a concise and yet comprehensive review of the Arabic text classification. We have covered over 50 research papers covering the past two decades (2000-2019). The main focus of this paper is to address the following issues: 1) The techniques reported in the literature including. 2) New Techniques. 3) Most claimed efficient technique. 4) Datasets used and which ones are most popular. 5) Which feature selection techniques are used? 6) Popular classes/categories used. 7) Effect of stemming techniques on classification results.

In this paper we conduct a comparative study between two stemming algorithms: khoja stemmer and our new stemmer for Arabic text classification (categorization), using Chisquare statistics as feature selection and focusing on decision tree classifier. Evaluation used a corpus that consists of 5070 documents independently classified into six categories: sport, entertainment, business, middle east, switch and world, on WEKA toolkit. The recall measure is used to compare the performance of these methods. Results show that text classification using our new stemmer outperforms classification using Khoja stemmer.

International Journal of Advanced Computer Science and Applications, 2015

Feature selection is necessary for effective text classification. Dataset preprocessing is essential to make upright result and effective performance. This paper investigates the effectiveness of using feature selection. In this paper we have been compared the performance between different classifiers in different situations using feature selection with stemming, and without stemming.Evaluation used a BBC Arabic dataset, different classification algorithms such as decision tree (D.T), Knearest neighbors (KNN), Naïve Bayesian (NB) method and Naïve Bayes Multinomial(NBM) classifier were used. The experimental results are presented in term of precision, recall, F-Measures, accuracy and time to build model.

International Journal of Database Theory and Application, 2016

Feature reduction are common techniques that used to improve the efficiency and accuracy of the document classification systems. The problems associated with these techniques are the highly dimensionality of the feature space and The difficulty of selecting the important features for understanding the document in question. The document usually consists of several parts and the important features that more closely associated with the topic of the document are appearing in the first parts or repeated in several parts of the document. Therefore, the position of the first appearance of a word and the compactness of the word considered as factors that determine the important features using the information within a document. This study, explored the impact of combining three feature weighting methods that depend on inverse document frequency (IDF), namely, Term frequency (TFiDF), the position of the first appearance of a word (FAiDF), and the compactness of the word (CPiDF) on the classification accuracy. In addition, we have investigated different feature selection techniques, namely, Information gain (IG), Goh and Low (NGL) coefficients, Chi-square Testing (CHI), and Galavotti-Sebastiani-Simi Coefficient (GSS) in order to improve the performance for Arabic document classification system. Experimental analysis on Arabic datasets reveals that the proposed methods have a significant impact on the classification accuracy, and in most cases the FAiDF feature weighting performed better than CPiDF and TFiDF. The results also clearly showed the superiority of the GSS over the other feature selection techniques and achieved 98.39% micro-F1 value when using a combination of TFiDF, FAiDF, and CPiDF as feature weighting method.

Journal of Engineering Science and Technology, 2017

Text classification is the process of assignment of unclassified text to appropriate classes based on their content. The most prevalent representation for text classification is the bag of words vector. In this representation, the words that appear in documents often have multiple morphological structures, grammatical forms. In most cases, this morphological variant of words belongs to the same category. In the first part of this paper, anew stemming algorithm was developed in which each term of a given document is represented by its root. In the second part, a comparative study is conducted of the impact of two stemming algorithms namely Khoja's stemmer and our new stemmer (referred to hereafter by origin-stemmer) on Arabic text classification. This investigation was carried out using chi-square as a feature of selection to reduce the dimensionality of the feature space and decision tree classifier. In order to evaluate the performance of the classifier, this study used a corpu...

2010

This research presents and compares the impact of text preprocessing, which has not been addressed before, on Arabic text classification using popular text classification algorithms;