Arabic text classification is a challenging task because of the complex morphology of the language, the existence of different writing forms and a multitude of dialects, which can result in sparser common text representations. While transformer models such as AraBERT have obtained superior results on many Arabic NLP tasks, their high computational requirements make them difficult to deploy in environments with limited hardware resources. In some cases this can also make the model less practical for researchers working with basic computer systems. This study focuses on a more practical issue: how much accuracy a simple classifier may lose when the amount of required computation is reduced. We use a combined TF-IDF representation based on both words and characters, then reduce the number of features using Chi-Square selection. The selected features are finally used with a linear SVM to create a model that is faster and more efficient, while still keeping good predictive performance. However, the method do not always provide the same level of accuracy as more complex models, especially with difficult text. The proposed lightweight method is tested against several other approaches, including word-based TF-IDF, character-based TF-IDF, Naive Bayes, Logistic Regression, BiLSTM, and AraBERT. All methods are tested using the same data distribution to make the comparison fair. The dataset used is the arbml/arabic_100k_reviews corpus, which originally contains 99,999 balanced reviews from three sentiment categories. After cleaning the data and removing very short reviews, the dataset was reduced to 99,759 samples. The training, validation, and testing sets includes 69,831, 9,976, and 19,952 reviews, respectively. This setup allows the different models to be compared under similar conditions and with the same evaluation process. After applying Chi-Square feature selection, the hybrid feature set was reduced from 250,000 to 50,000 dimensions, which represents an 80% reduction. That proposed method achieved 67.90% accuracy and a Macro-F1 score of 67.75%. Its training time was around 41 seconds, while the complete test set was processed in about 0.03 seconds. Among all the evaluated models, AraBERT achieved the best overall performance, reaching 74.08% accuracy and 74.25% Macro-F1. However, its computational requirements were much higher, with nearly 1,760 seconds needed for training and about 47 seconds for inference on the same test set. Depending on the processing stage, this makes AraBERT approximately 40 to 1,500 times slower than the proposed lightweight approach. The proposed method is therefore not presented as a replacement for AraBERT in terms of accuracy, since its accuracy is lower. Instead, its main advantage is the considerable and measurable reduction in computational cost. This trade-off can be useful in situations where GPU availability, memory capacity, or response time are limited.
The primary objective of this paper is to introduce a new concept of fibrewise topological spaces on D is named fibrewise multi- topological spaces on D. Also, we entroduce the concepts of multi-proper, fibrewise multi-compact, fibrewise locally multi-compact spaces, Moreover, we study relationships between fibrewise multi-compact (resp., locally multi-compac) space and some fibrewise multi-separation axioms.
The study aims at analyzing the inconsistent structural and semantic aspects found in the plays of N.A Ostrovsky. The analysis, that includes all the linguistics schools of thoughts in modern Russian language, is performed chronologically to clarify all the ambiguities that the Russian language learners may face. Such difficulties lie in the use of inconsistent aspects with complete declarative sentences and adverbial clauses. Hence, it constructs a new sentence category that consists of secondary clause and its syncretism semantic.
The study illustrates the wide scope of both studying the sentence inconsistent
... Show More
The aim of this research is to study some types of fibrewise fuzzy topological spaces. The six major goals are explored in this thesis. The very first goal, introduce and study the notions types of fibrewise topological spaces, namely fibrewise fuzzy j-topological spaces, Also, we introduce the concepts of fibrewise j-closed fuzzy topological spaces, fibrewise j-open fuzzy topological spaces, fibrewise locally sliceable fuzzy j-topological spaces and fibrewise locally sectionable fuzzy j-topological spaces. Furthermore, we state and prove several Theorems concerning these concepts, where j={δ,θ,α,p,s,b,β} The second goal is to introduce weak and strong forms of fibrewise fuzzy ω-topological spaces, namely the fibrewise fuz
... Show MoreThe research aims to apply a modified SERVQUAL model to evaluate the quality of the educational services via conducting exploratory research for students from the College of Administration and Economics- Department of Business Administration- Evening studies at the University of Baghdad. Questionnaire of two parts was distributed to a sample of (72) students out of (720) students of the 2nd.,3rd. and 4th. year in the beginning of the second semester of the year 2008-2009 to measure the expectations and perceptions to the quality of the educational services. Five major dimensions were analyzed to see the gaps for (22) variables. The study concluded that there were (13) variables confirmed that the
... Show More
(5)
(3)
(25)
Jean-Paul Sartre and Badr Shakir al-Sayyabe are among the most prominent writers that critiqued the destructive role of capitalism and the patriarchal power system in the period of the Post-World War II crisis. Divided into three chapters, the present study examines two of the most eminent literary works in the history of the Western and Eastern societies in the fifties of the last decade: Jean Paul Sartre’s play : The Respectful Prostitute and Badr Shaker al-Sayyabe’s poem: The Blind Prostitute.
Chapter one discusses the position of the prostitute in a patriarchal societies. Chapter two linguistically analy
... Show More