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.
In this study water quality was indicated in terms of Water Quality Index that was determined through summarizing multiple parameters of water test results. This index offers a useful representation of the overall quality of water for public or any intended use as well as indicating pollution, water quality management and decision making. The application of Water Quality Index
(WQI) with sixteen physicochemical water quality parameters was performed to evaluate the quality of Tigris River water for drinking usage. This was done by subjecting the water samples collected from eight stations in Baghdad city during the period 2004-2010 to comprehensive physicochemical analysis. The sixteen physicochemical parameters included: Turbidity, A
(7)
Abstract Throughout this paper R represents commutative ring with identity and M is a unitary left R-module, the purpose of this paper is to study a new concept, (up to our knowledge), named St-closed submodules. It is stronger than the concept of closed submodules, where a submodule N of an R-module M is called St-closed (briefly N ≤Stc M) in M, if it has no proper semi-essential extensions in M, i.e if there exists a submodule K of M such that N is a semi-essential submodule of K then N = K. An ideal I of R is called St-closed if I is an St-closed R-submodule. Various properties of St-closed submodules are considered.
(5)
The study of surface hardness, wear resistance, adhesion strength, electrochemical corrosion resistance and thermal conductivity of coatings composed from sodium silicate was prepared using graphite micro-size particles and carbon nano particles as fillers respectively of concentration of (1-5%), for the purpose of covering and protecting the oil distillation towers. The results showed that the sodium silicate coating reinforced with carbon nano-powder has higher resistance to stitches, mechanical wear, adhesive and thermal conductivity than graphite/sodium silicate composite especially when the ratio 5% and 1%, the electrochemical corrosion test confirmed that the coating process of stainless steel 304 lead to increasin
... Show MoreIn this study water quality was indicated in terms of Water Quality Index that was determined through summarizing multiple parameters of water test results. This index offers a useful representation of the overall quality of water for public or any intended use as well as indicating pollution, water quality management and decision making. The application of Water Quality Index (WQI) with sixteen physicochemical water quality parameters was performed to evaluate the quality of Tigris River water for drinking usage. This was done by subjecting the water samples collected from eight stations in Baghdad city during the period 2004-2010 to comprehensive physicochemical analysis. The sixteen physicochemical parameters included: Turbidity,
... Show MoreResumen
Sotileza , localismo santandrino de sutileza , es la parte más fina del aparejo de pescar donde va el anzuelo. Es la obra maestro de José María de Pereda.Su ambiente , el Santander viejo, anterior al año 50,evocado emocionadamente - emociόn romántica contenida en los trazos sobrios y firmes de un naturalism psicolόgico y paisajista,el Santander que el autor confiesa poseer en el fondo de su corazόn,«y tenerlo esculpido en la memoria de tal suerte que ,a ojos cerrados,me atrevería a trazarle con todo su perímetro y sus calles, y el color de sus piedras, y el número, y los nombres, y hasta las caras de sus habitantes».Dentro de la grandeza primaria de las criaturas de Pere
... Show MoreIn this paper, an algorithm for binary codebook design has been used in vector quantization technique, which is used to improve the acceptability of the absolute moment block truncation coding (AMBTC) method. Vector quantization (VQ) method is used to compress the bitmap (the output proposed from the first method (AMBTC)). In this paper, the binary codebook can be engender for many images depending on randomly chosen to the code vectors from a set of binary images vectors, and this codebook is then used to compress all bitmaps of these images. The chosen of the bitmap of image in order to compress it by using this codebook based on the criterion of the average bitmap replacement error (ABPRE). This paper is suitable to reduce bit rates
... Show More
The Disi water samples were collected from different Disi aquifer wells in Jordan using a clean polyethylene container of 10-liter size. A hyper-pure germanium (HPGe) detector with high- resolution gamma-ray spectroscopy and a low background counting system was used for the identification of unknown gamma-rays emitting from radionuclides in the environmental samples. The ranges of specific activity concentrations of 226Ra and 228Ra in the Disi aquifer water were found to be from 0.302 ± 0.085 to 0.723 ± 0.207 and from 0.047 ± 0.010 to 0.525 ± 0.138 Bq L−1, with average values of 0.516 ± 0.090 and 0.287 ± 0.091 Bq L−1, respectively. The average combined radium (226Ra + 228Ra) activity and radium activity ratio (228Ra/226Ra) in Disi
... Show More
(5)
This paper including a gravitational lens time delays study for a general family of lensing potentials, the popular singular isothermal elliptical potential (SIEP), and singular isothermal elliptical density distribution (SIED) but allows general angular structure. At first section there is an introduction for the selected observations from the gravitationally lensed systems. Then section two shows that the time delays for singular isothermal elliptical potential (SIEP) and singular isothermal elliptical density distributions (SIED) have a remarkably simple and elegant form, and that the result for Hubble constant estimations actually holds for a general family of potentials by combining the analytic results with data for the time dela
... Show More
(17)
(13)
The present study was conducted to investigate the relationship between critical thinking, epistemological beliefs, and learning strategies with the academic performance of high school first-grade male and female students in Yazd. For this purpose, from among all first-grade students, as many as 250 students (130 females and 120 males) were selected by using multistage cluster sampling. The data needed were then collected through using California Critical Thinking Skills Test, Schommer's Epistemological Beliefs Questionnaire, Biggs’ Revised Two Factor Study Process Questionnaire. The findings indicated that there is a positive significant relationship between critical thinking and academic performance and achievement. Moreover, four fa
... Show More