Clustering Arabic text documents is of high importance for many Natural Language Technologies. This study uses a combined method to cluster Arabic text documents. Mainly, we use generative models and clustering techniques. The study uses Latent Dirichlet Allocation (LDA) and kmeans clustering algorithm and applies them to a news dataset used in previous similar studies. The aim of this research is twofold: it first shows that normalizing the weights in the vector space, for the documentterm matrix of the text documents, dramatically improves the quality of clusters and hence the accuracy of clustering when using k-means algorithm. The results are compared to a recent study on clustering Arabic text documents. Second, it shows that the combined method is superior in terms of clustering quality for Arabic text documents according to external measures like purity, F-measure, entropy, accuracy, and other measures. It is shown in this study that the purity of the combined method is 0.933 compared to 0.82 for K-means algorithm, these figures are higher in comparison to a recent similar study. This is also confirmed by the other used validation measures. The correctness of the combined method is then confirmed using different Arabic datasets.

Categorizing Arabic text documents is considered an important research topic in the field of Natural Language Processing (NLP) and Machine Learning (ML). The number of Arabic documents is tremendously increasing daily as new web pages, news articles, social media contents are added. Hence, classifying such documents in specific classes is of high importance to many people and applications. Convolutional Neural Network (CNN) is a class of deep learning that has been shown to be useful for many NLP tasks, including text translation and text categorization for the English language. Word embedding is a text representation currently used to represent text terms as real-valued vectors in vector space that represent both syntactic and semantic traits of text. Current research studies in classifying Arabic text documents use traditional text representation such as bag-of-words and TF-IDF weighting, but few use word embedding. Traditional ML algorithms have already been used in Arabic text categorization, and good results are achieved. In this study, we present a Multi-Kernel CNN model for classifying Arabic news documents enriched with n-gram word embedding, which we call A Superior Arabic Text Categorization Deep Model (SATCDM). The proposed solution achieves very high accuracy compared to current research in Arabic text categorization using 15 of freely available datasets. The model achieves an accuracy ranging from 97.58% to 99.90%, which is superior to similar studies on the Arabic document classification task.

Semantic Text Similarity (STS) has several and important applications in the field of Natural Language Processing (NLP). The Aim of this study is to investigate the effect of stemming on text similarity for Arabic language at sentence level. Several Arabic light and heavy stemmers as well as lemmatization algorithms are used in this study, with a total of 10 algorithms. Standard training and testing data sets are used from SemEval-2017 international workshop for Task 1, Track 1 Arabic (ar–ar). Different features are selected to study the effect of stemming on text similarity based on different similarity measures. Traditional machine learning algorithms are used such as Support Vector Machines (SVM), Stochastic Gradient Descent (SGD) and Naïve Bayesian (NB). Compared to the original text, using the stemmed and lemmatized documents in experiments achieve enhanced Pearson correlation results. The best results attained when using Arabic light Stemmer (ARLSTem) and Farasa light stemmers, Farasa and Qalsadi Lemmatizers and Tashaphyne heavy stemmer. The best enhancement was about 7.34% in Pearson correlation. In general, stemming considerably improves the performance of sentence text similarly for Arabic language. However, some stemmers make results worse than those for original text; they are Khoja heavy stemmer and AlKhalil light stemmer.

Chaos provides many interesting properties that can be used to achieve computational tasks. Such properties are sensitivity to initial conditions, space filling, control and synchronization. Chaotic neural models have been devised to exploit such properties. In this paper, a chaotic spiking neuron model is investigated experimentally. This investigation is performed to understand the dynamic behaviours of the model. The aim of this research is to investigate the dynamics of the nonlinear dynamic state neuron (NDS) experimentally. The experimental approach has revealed some quantitative and qualitative properties of the NDS model such as the control mechanism, the reset mechanism, and the way the model may exhibit dynamic behaviours in phase space. It is shown experimentally in this paper that both the reset mechanism and the self-feed back control mechanism are important for the NDS model to work and to stabilise to one of the large number of available unstable periodic orbits (UPOs) that are embedded in its attractor. The experimental investigation suggests that the internal dynamics of the NDS neuron provide a rich set of dynamic behaviours that can be controlled and stabilised. These wide range of dynamic behaviours may be exploited to carry out information processing tasks