Search

Speech recognition is a critical task in spoken language applications. Globally known models such as DeepSpeech2 are effective for English speech recognition, however, they are not well-suited for languages like Arabic. This paper is interested in recognizing the Arabic language, especially Modern Standard Arabic (MSA). This paper proposed two models that utilize "Franco-Arabic" as an encoding mechanism and additional enhancements to recognize MSA. The first model uses Mel-Frequency Cepstral Coefficients (MFCCs) as input features, while the second employs six sequential Gated Recurrent Unit (GRU) layers. Each model is then followed by a fully connected layer with a dropout layer which helped reduce overfitting. The Connectionist Temporal Classification (CTC) loss is used to calculate the prediction error and to maximize the correct transcription likelihood. Two experiments were conducted for each model. The first experiment involved 41 h of continuous speech over 15 epochs. Whereas, the second one utilized 69 h over 30 epochs. The experiments showed that the first model excels in speed while the second excels in accuracy, and both outperformed the well-known DeepSpeech2. [ABSTRACT FROM AUTHOR]

Sign language is an essential means of communication for individuals with hearing disabilities. However, there is a significant shortage of sign language interpreters in some languages, especially in Saudi Arabia. This shortage results in a large proportion of the hearing-impaired population being deprived of services, especially in public places. This paper aims to address this gap in accessibility by leveraging technology to develop systems capable of recognizing Arabic Sign Language (ArSL) using deep learning techniques. In this paper, we propose a hybrid model to capture the spatio-temporal aspects of sign language (i.e., letters and words). The hybrid model consists of a Convolutional Neural Network (CNN) classifier to extract spatial features from sign language data and a Long Short-Term Memory (LSTM) classifier to extract spatial and temporal characteristics to handle sequential data (i.e., hand movements). To demonstrate the feasibility of our proposed hybrid model, we created a dataset of 20 different words, resulting in 4000 images for ArSL: 10 static gesture words and 500 videos for 10 dynamic gesture words. Our proposed hybrid model demonstrates promising performance, with the CNN and LSTM classifiers achieving accuracy rates of 94.40% and 82.70%, respectively. These results indicate that our approach can significantly enhance communication accessibility for the hearing-impaired community in Saudi Arabia. Thus, this paper represents a major step toward promoting inclusivity and improving the quality of life for the hearing impaired. [ABSTRACT FROM AUTHOR]

This paper examines the syntax of additive compound numerals in Modern Standard Arabic (MSA), uncovering their unique properties related to number morphology, definiteness, and Case assignment within numeral–noun constructions. These properties necessitate a constituency analysis which reveals that compound numerals have the structure of copulative compounds in MSA, and they are phrases, not functional heads. Drawing on the distinction between inherent, lexical, and structural Cases, this paper posits that the accusative Case on the numerals is an inherent Case, inaccessible to syntactic transformations. Furthermore, the analysis of numeral–noun constructions as numerically quantified phrases (NQPs) explains the assignment of a structural accusative Case or the inherent genitive Case on the quantified noun, based on the overtness of NQ0. Finally, the paper addresses the intriguing question of how NQPs in MSA, despite lacking a nominative Case, can assume the subject position and govern agreement in both verbal and verbless sentences. [ABSTRACT FROM AUTHOR]

Copyright of Al-Adab / Al-ādāb is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pretrained language models have achieved great success in various natural language understanding (NLU) tasks due to their capacity to capture deep contextualized information in text using pretraining on large-scale corpora. Tokenization plays a significant role in the process of lexical analysis. Tokens become the input for other natural language processing (NLP) tasks, like semantic parsing and language modeling. However, there is a lack of research on the evaluation of the impact of tokenization on the Arabic language model. Therefore, this study aims to address this gap in the literature by evaluating the performance of various tokenizers on Arabic large language models (LLMs). In this paper, we analyze the differences between WordPiece, SentencePiece, and BBPE tokenizers by pretraining three BERT models using each tokenizer while measuring the performance of each model on seven different NLP tasks using 29 different datasets. Overall, the model pretrained with text tokenized using the SentencePiece tokenizer significantly outperforms the other two models that utilize WordPiece and BBPE tokenizers. The results of this paper will assist researchers in developing better models, making better decisions in selecting the best tokenizers, improving feature engineering, and making models more efficient, thus ultimately leading to advancements in various NLP applications. [ABSTRACT FROM AUTHOR]

The paper provides a novel motivation in favor of a complex and fine-grained syntax of spatial PPs in Arabic. It neatly fills a gap between the complex semantics of spatial expressions and their morphosyntax, which remains unexplained using wide spread cognitive approaches. We propose a fine-grained architecture of root nodes, categories, and features in the basic representations of Path/Place expressions, inspired by cartographic analyses of PPs, but based on a pP dual-projection model, separating the root/lexical part from the functional/categorial part, as in Distributed Morphology (=DM). In so doing, the paper challenges traditional analyses of PPs as projecting a uniform Path over Place structure (with no bifurcating domain separation). It also provides essential ingredients allowing the decomposition of Place and Path words or expressions, including COINCIDENCE, CONTAIN, CONTACT, etc., or syntactic projections such AxPs, DeixPs, DegPs, ScaleP, GoalPs, etc., which play important syntactico-semantic roles in the grammar. Our analysis successfully accounts for complexity of prepositions or spatial expressions, their morphosyntactic alternations, variation, and polysemy. [ABSTRACT FROM AUTHOR]

This paper provides a constraint-based analysis of the syllable structure of onset consonant sequences in Najdi Arabic, spoken in central Saudi Arabia. Unlike Classical or Standard Arabic, Najdi is believed to allow consonant clusters in the onset. The study tested two assumptions. The first is that Najdi onset clusters result from a vowel deletion process, leading to different kinds of clusters with distinct sonority hierarchies and that these form complex onsets. The second is that Najdi inputs are different from Classical or Standard Arabic, in which there is no vowel in the underlying representation and hence no deletion occurs, resulting in simplex onsets. The paper adopted optimality theory to analyze the data, considering a phenomenon that occurs in the speech of Najdi speakers. Following this framework, constraints were utilized to demonstrate the syllable structure of the onset clusters in Najdi according to the above assumptions. The results revealed consonant sequences rather than consonant clusters, meaning the consonants were not parsed in the same syllable, agreeing with previous acoustic research. [ABSTRACT FROM AUTHOR]

This study is the first to explore language attitudes of the endangered Faifi language in SA. Understanding these attitudes is crucial for future language revitalization efforts. Employing a conceptual framework from LA research, data were collected via an online Arabic questionnaire with a sample of 258 participants. This paper aims to explore the indigenous people's language attitudes, frequency of language use, and the influence of social backgrounds. Data were analyzed using factor analysis and multiple regression. Three key findings emerged: Firstly, a two-dimensional model encompassing status and dynamism dimensions was identified, offering new insights into LAs. Notably, the trait "educated" was associated with dynamism rather than the typical association with the status dimension, which can be attributed to educational factors related to the Faifi language's lack of formal instruction in schools. Secondly, the reported use of the Faifi language by its speakers indicated a positive trend. Lastly, age was found to be the only significant sociodemographic variable, with older participants exhibiting more positive attitudes compared to younger participants. In summary, this research contributes fresh perspectives on the dimensions of language attitudes, particularly by highlighting the deviation of the trait "educated" from its customary position within the status dimension. Additionally, the study emphasizes the salience of age as a factor. The paper recommends macro and micro language policies; macro language policy should consider integrating the language into the educational system, while micro language policy should originate from the indigenous community itself, initiating initiatives to further support language use among young speakers. [ABSTRACT FROM AUTHOR]

Multilingual large language models (MLLMs) have demonstrated remarkable performance across a wide range of cross-lingual Natural Language Processing (NLP) tasks. The emergence of MLLMs made it possible to achieve knowledge transfer from high-resource to low-resource languages. Several MLLMs have been released for cross-lingual transfer tasks. However, no systematic evaluation comparing all models for Arabic cross-lingual Named-Entity Recognition (NER) is available. This paper presents a benchmark evaluation to empirically investigate the performance of the state-of-the-art multilingual large language models for Arabic cross-lingual NER. Furthermore, we investigated the performance of different MLLMs adaptation methods to better model the Arabic language. An error analysis of the different adaptation methods is presented. Our experimental results indicate that GigaBERT outperforms other models for Arabic cross-lingual NER, while language-adaptive pre-training (LAPT) proves to be the most effective adaptation method across all datasets. Our findings highlight the importance of incorporating language-specific knowledge to enhance the performance in distant language pairs like English and Arabic. [ABSTRACT FROM AUTHOR]

The detection of toxic language in the Arabic language has emerged as an active area of research in recent years, and reviewing the existing datasets employed for training the developed solutions has become a pressing need. This paper offers a comprehensive survey of Arabic datasets focused on online toxic language. We systematically gathered a total of 54 available datasets and their corresponding papers and conducted a thorough analysis, considering 18 criteria across four primary dimensions: availability details, content, annotation process, and reusability. This analysis enabled us to identify existing gaps and make recommendations for future research works. For the convenience of the research community, the list of the analysed datasets is maintained in a GitHub repository. [ABSTRACT FROM AUTHOR]

Background: The clinical learning environment (CLE) plays a crucial role in shaping the learning experiences and professional development of medical professionals. Understanding and optimising this environment is essential for improving doctors' knowledge acquisition, clinical skills, and overall well-being. The development of the Postgraduate Hospital Educational Environment Measure (PHEEM) and its translation to numerous languages has been a milestone in clinical education. Even though PHEEM was recently translated into Arabic, its psychometric properties in this form remain unevaluated. Therefore, this study aims to conduct a comprehensive psychometric analysis of the Arabic version of the PHEEM questionnaire. Methods: This is a cross-sectional questionnaire survey validation study. The defined population were medical residents in Damascus, Syria. A paper-based survey as well as an online-based one were conducted using several non-probability sampling methods namely, convenience, river and, snowball sampling between June 15, 2023, and June 21, 2023. Both exploratory (EFA) and confirmatory (CFA) factor analyses were conducted. Several psychometric criteria were applied including scree plot, eigenvalue > 1.5 and the 'proportion of variance accounted for' criterion. Results: A total of 543 participants completed the questionnaire (56.9% female). Kaiser-Meyer-Olkin measure for sample adequacy was high (0.937) and the P-value for Bartlett's test was < 0.001. EFA revealed five meaningful factors which were labelled: perception of teachers, learner's engagement and social participation, external regulation, work culture, and living conditions. These factors had the following eigenvalues: 12.6, 2.18, 2.03, 1.86, and 1.41 respectively, with a total explained variance of 43.45%. Cronbach's Alpha was 0.938. CFA confirmed the model structure of EFA (SRMR = 0.067 and RMSEA = 0.066). The Average Variance Explained (AVE) value of any given factor was > 0.7. Discussion: The Arabic PHEEM inventory demonstrated satisfactory psychometric properties. The extracted domains are of theoretical relevance to the psychosocial-material conceptual framework for learning environment. Nonetheless, this validation was performed in the Syrian context; therefore, future studies in other Arabic countries are recommended to support the applicability of Arabic PHEEM in the wide Arab World. [ABSTRACT FROM AUTHOR]

The research presented in the following paper focuses on the effectiveness of a modern standard Arabic corpus, AraFast, in training transformer models for natural language processing tasks, particularly in Arabic. In the study described herein, four experiments were conducted to evaluate the use of AraFast across different configurations: segmented, unsegmented, and mini versions. The main outcomes of the present study are as follows: Transformer models trained with larger and cleaner versions of AraFast, especially in question-answering, indicate the impact of corpus quality and size on model efficacy. Secondly, a dramatic reduction in training loss was observed with the mini version of AraFast, underscoring the importance of optimizing corpus size for effective training. Moreover, the segmented text format led to a decrease in training loss, highlighting segmentation as a beneficial strategy in Arabic NLP. In addition, using the study findings, challenges in managing noisy data derived from web sources are identified, which were found to significantly hinder model performance. These findings collectively demonstrate the critical role of well-prepared, segmented, and clean corpora in advancing Arabic NLP capabilities. The insights from AraFast's application can guide the development of more efficient NLP models and suggest directions for future research in enhancing Arabic language processing tools. [ABSTRACT FROM AUTHOR]

Computer-assisted language learning (CALL) systems increasingly arouse a significant interest and establish a presence in automated foreign language learning. They enhance traditional learning methods by providing access to various accents and spoken language styles through websites, mobile applications, and social media. Herein, mispronunciation detection is a key component mainly addressed as a classification problem. Meanwhile, deep learning (DL) advances have promoted these systems by training deep neural networks (DNN) to classify a pronunciation as correct or incorrect. However, the effectiveness of the DL models is hindered by many shortcomings, such as the scarcity of labeled data. To address this issue, the paper assumes an anomaly detection-based mispronunciation detection approach. It utilizes a variational autoencoder (VAE) relying on a density-based method to model the "normal data." The VAE is a generative model trained in a self-supervised way to learn the distribution of the correct pronunciations, standing for "normal data," and is expected to detect mispronunciations, standing for "abnormal data" during the test stage. Our proposition was evaluated in the context of Arabic pronunciation learning through the ASMDD Arabic dataset. The obtained results are promising, with an accuracy of about 98%. The proposed VAE outperformed the standard autoencoder as well as the state-of-the-art convolution neural networks used for Arabic mispronunciation detection. [ABSTRACT FROM AUTHOR]

This study explores some euphemistic expressions in common usage in the Kingdom of Saudi Arabia (KSA). It evaluates the degree to which Saudis are familiar with these expressions and how frequently they use them. The KSA covers a large area with a variety of dialects: thus, any socio-linguistic research which deals with slang should be meticulous. One enabling factor for this study is that Saudis are comparatively religious and avoidant of linguistic taboos, and consequently employ euphemisms often. Several research papers have tackled taboos in the KSA, but most of these have been contrastive to or comparative with British English or American English, while others have explored standard euphemistic expressions in classical Arabic. This study is unique in dealing with selective euphemisms used in Saudi slang through a survey devised to measure peoples' degree of knowledge as well as their usage of such expressions. After analyzing the results of the questionnaires, it is possible to derive several attitudinal results, the most important of which include the findings that present-day Saudis are generally well-acquainted with euphemism in their language and that they are inclined to employ it in everyday situations wherever appropriate. The population selected for this study is resident within the Al Riyadh region, or what can be called "Najid". As the heart of the KSA, this region has Saudis from various regions and with a range of linguistic differences. However, it is recommended that similar studies be taken up in different parts of the KSA so as to pinpoint regional variations. [ABSTRACT FROM AUTHOR]

As a well-established strategy in the educational traditions of Islam, copying texts (imitating a model) has played a crucial role in learning the Holy Quran and the Arabic language. This study delves into the necessity of understanding how this traditional strategy influences the learning of foreign languages. Using 18 hours of strategy-based instruction, this paper examines the efficacy of text copying in learning grammar (independent variable), as evidenced by a series of grammar tests and surveys assessing learners' perceptions (dependent variables). The study draws upon data from two groups of college-level English as Foreign Language (EFL) learners, comprising a control group (n=10) and an experimental group (n=11), all categorized at the A2 proficiency level according to the Common European Framework of Reference for Languages (CEFR). The findings suggest that text copying enhances learners' grammatical understanding and contributes to overall satisfaction in learning a foreign language, as indicated by improved test scores and positive learner feedback. [ABSTRACT FROM AUTHOR]

This paper outlines the implementation of a spell checker for the Arabic language, leveraging the capabilities of NooJ and its functionality, specifically noojapply. In this paper, we shall proceed to provide clear definitions and comprehensive descriptions of several categories of spelling errors. Next, we will provide a comprehensive introduction to the NooJ platform and its command-line utility, noojapply. In the subsequent section, we shall outline the four main phases of our spell checker prototype. We intend to develop a local grammar in NooJ for the purpose of error detection. Afterwards, a morphological grammar and a local grammar will be created in NooJ with the aim of providing an exhaustive list of possible corrections. Following that, a revised algorithm will be employed to arrange these candidates in descending order of ranking. Subsequently, a web user interface will be developed to visually represent our research efforts. Finally, we will proceed to showcase a series of tests and evaluations conducted on our prototype, Al Mudaqiq. [ABSTRACT FROM AUTHOR]

The automatic speech identification in Arabic tweets has generated substantial attention among academics in the fields of text mining and natural language processing (NLP). The quantity of studies done on this subject has experienced significant growth. This study aims to provide an overview of this field by conducting a systematic review of literature that focuses on automatic hate speech identification, particularly in the Arabic language. The goal is to examine the research trends in Arabic hate speech identification and offer guidance to researchers by highlighting the most significant studies published between 2018 and 2023. This systematic study addresses five specific research questions concerning the types of the Arabic language used, hate speech categories, classification techniques, feature engineering techniques, performance metrics, validation methods, existing challenges faced by researchers, and potential future research directions. Through a comprehensive search across nine academic databases, 24 studies that met the predefined inclusion criteria and quality assessment were identified. The review findings revealed the existence of many Arabic linguistic varieties used in hate speech on Twitter, with modern standard Arabic (MSA) being the most prominent. In identification techniques, machine learning categories are the most used technique for Arabic hate speech identification. The result also shows different feature engineering techniques used and indicates that N-gram and CBOW are the most used techniques. F1-score, precision, recall, and accuracy were also identified as the most used performance metric. The review also shows that the most used validation method is the train/test split method. Therefore, the findings of this study can serve as valuable guidance for researchers in enhancing the efficacy of their models in future investigations. Besides, algorithm development, policy rule regulation, community management, and legal and ethical consideration are other real-world applications that can be reaped from this research. [ABSTRACT FROM AUTHOR]

Copyright of Jordanian Journal of Computers & Information Technology is the property of Jordanian Journal of Computers & Information Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The effectiveness of existing AI detectors is notably hampered when processing Arabic texts. This study introduces a novel AI text classifier designed specifically for Arabic, tackling the distinct challenges inherent in processing this language. A particular focus is placed on accurately recognizing human-written texts (HWTs), an area where existing AI detectors have demonstrated significant limitations. To achieve this goal, this paper utilized and fine-tuned two Transformer-based models, AraELECTRA and XLM-R, by training them on two distinct datasets: a large dataset comprising 43,958 examples and a custom dataset with 3078 examples that contain HWT and AI-generated texts (AIGTs) from various sources, including ChatGPT 3.5, ChatGPT-4, and BARD. The proposed architecture is adaptable to any language, but this work evaluates these models' efficiency in recognizing HWTs versus AIGTs in Arabic as an example of Semitic languages. The performance of the proposed models has been compared against the two prominent existing AI detectors, GPTZero and OpenAI Text Classifier, particularly on the AIRABIC benchmark dataset. The results reveal that the proposed classifiers outperform both GPTZero and OpenAI Text Classifier with 81% accuracy compared to 63% and 50% for GPTZero and OpenAI Text Classifier, respectively. Furthermore, integrating a Dediacritization Layer prior to the classification model demonstrated a significant enhancement in the detection accuracy of both HWTs and AIGTs. This Dediacritization step markedly improved the classification accuracy, elevating it from 81% to as high as 99% and, in some instances, even achieving 100%. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Research in Language & Translation (JRLT) is the property of Journal of Research in Language & Translation (JRLT) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Automatic Speech Recognition (ASR) systems have witnessed significant advancements in recent years, thanks to the emergence of deep learning techniques and the availability of large speech datasets in various languages. With the increasing demand for Arabic voice-enabled technologies, the availability of a high-quality and representative dataset for the Arabic language becomes crucial. This paper presents the development of a new dataset called ArabAlg, specifically designed for Arabic Speech Command Recognition (ASCR), to support the integration of Arabic voice recognition systems into smart devices in the Internet of Things (IoT). This research focuses on collecting and annotating a diverse range of Arabic speech commands, encompassing various domains and applications. The dataset construction process involves recording and preprocessing several utterances from native Arabic speakers. To ensure precision and reliability, quality control measures are implemented during data collection and annotation. The resulting dataset provides a valuable resource for training and evaluating ASCR systems tailored for Arabic speakers using Machine Learning and Deep Learning. [ABSTRACT FROM AUTHOR]

Copyright of Lenguas Modernas is the property of Universidad de Chile, Facultad de Filosofia y Humanidades and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Izdihar: Journal of Arabic Language Teaching, Linguistics & Literature is the property of Universitas Muhammadiyah Malang and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Since it started in February 2022, the Russian-Ukrainian War has gained the interest of numerous news organizations. The reframing of visual elements of ten news items about the Russian-Ukrainian War is examined in this study. The Arabic versions are extracted from the Al Jazeera website, while the original articles were taken from The Atlantic and Foreign Affairs. Baker's narrative theory is used in this paper (Baker, 2018). Comparing the visual elements in the English articles to their Arabic equivalents allowed researchers to pinpoint how they are paratextually reframed in the translated versions. The findings showed that Al Jazeera occasionally produces various, varied, and incongruent interpretations of the narrative. This could lead to multiple and, occasionally, dissimilar perspectives on the same story. The findings showed that Al Jazeera utilized paratextual reframing strategies involving visual elements, such as images, videos, and typographical features, to reframe the Russian-Ukrainian War. The research suggests that while the original media outlets initially framed the war according to their agenda, Al Jazeera altered this frame in the translated text. As a result, the target audience's perception of the event under examination may change during the entire process. [ABSTRACT FROM AUTHOR]

We have developed in this paper a morphological disambiguation hybrid system for the Arabic language that identifies the stem, lemma and root of a given sentence words. Following an out-of-context analysis performed by the morphological analyser Alkhalil Morpho Sys, the system first identifies all the potential tags of each word of the sentence. Then, a disambiguation phase is carried out to choose for each word the right solution among those obtained during the first phase. This problem has been solved by equating the disambiguation issue with a surface optimization problem of spline functions. Tests have shown the interest of this approach and the superiority of its performances compared to those of the state of the art. [ABSTRACT FROM AUTHOR]

The present study investigates the concept of false friends in two genetically unrelated languages: Arabic and English. It provides explanations for the source of possible confusion and misunderstanding caused by false friends in contemporary Arabic and English. It also highlights the nomenclature related to false friends where they can be classified into two categories: absolute false friends and partial false friends. The study explicates how false friendship, as a linguistic phenomenon, can be a real hurdle to communication among the learners and teachers of a certain language. The etymological development of some words is very important to explain how false friendship occurs. Morphologically, some special cases of intralingual morphological false friends are explored in so far as they are related to the concept of false friendship to put them into a certain linguistic framework. [ABSTRACT FROM AUTHOR]

Textual emotion recognition (TER) has significant commercial potential since it can be used as an excellent tool to monitor a brand/business reputation, understand customer satisfaction, and personalize recommendations. It is considered a natural language processing task that can be used to understand and classify emotions such as anger, happiness, and surprise being conveyed in a piece of text (product reviews, tweets, and comments). Despite the advanced development of deep learning and particularly transformer architectures, Arabic-focused models for emotion classification have not achieved satisfactory accuracy. This is mainly due to the morphological richness, agglutination, dialectal variation, and low-resource datasets of the Arabic language, as well as the unique features of user-generated text such as noisiness, shortness, and informal language. This study aims to illustrate the effectiveness of large language models on Arabic multi-label emotion classification. We evaluated GPT-3.5 Turbo and GPT-4 using three different settings: in-context learning, emotional stimuli prompt, and fine-tuning. The ultimate objective of this research paper is to determine if these LLMs, which have multilingual capabilities, could contribute to enhancing the aforementioned task and encourage its use within the context of an e-commerce environment for example. The experimental results indicated that the fine-tuned GPT-3.5 Turbo model achieved an accuracy of 62.03%, a micro-averaged F1-score of 73%, and a macro-averaged F1-score of 62%, establishing a new state-of-the-art benchmark for the task of Arabic multi-label emotion recognition. [ABSTRACT FROM AUTHOR]

Topic Modeling approaches face difficulties in processing legal texts because of their unique characteristics, such as the length of the texts and the specialized terminology used within them. The process of topic modeling involves finding a text's semantic structure. This way, specific approaches are needed. When the legal documents are presented has a lot to do with what topics are important. This paper aims to explain and evaluate BERTopic's application to topic modeling in legal documents. In this research, we experiment with BERTopic by utilizing its several pre-trained Arabic language models as embeddings. Performance evaluation employs the Normalized Pointwise Mutual Information (NPMI) measure. Notably, in comparison to multilingual pre-trained models, our findings reveal that BERTopic using Arabic monolingual pre-trained models exhibits superior performance, offering insights into sustainable and efficient topic modeling for legal documents. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Question Answering Systems (QAS) are made to automatically provide accurate response to user questions that are phrased in natural language. Most of the existing QAS adopting traditional representations like word embedding and bag-of-words, have shown promising results. However, only a few works take into account the contextual information and meaning within texts to extract answers from huge sources of information. Moreover, dealing with Arabic open-domain question-answering systems is still challenging due to its rich morphology and ambiguity of words. To address these limitations, we introduce, in this study, a novel QA approach for the Arabic language that is based on passage retrieval and Sentence Embedding (SE) representation. It consists of three steps: (1) Question classification and query formulation, (2) Documents and passages retrieval, and (3) Answers extraction. In this work, we make use of the AraBERT transformer model to compute vector representation. This allows for considering both implicit semantics and the words' context within the text. Furthermore, in order to collect potential passages for user questions, we investigate a method for retrieving Arabic passages using the BM25 model, a query expansion process, and SE representation. The final answer is generated by fine-tuning AraBERT parameters and ranking passages so that the most relevant ones can be extracted. To assess our approach, we carried out several experiments on CLEF and TREC datasets using two different taxonomies. The obtained results show that the proposed method achieves 92% in terms of F1-score. [ABSTRACT FROM AUTHOR]

This paper examines the utilization of Arabic tautological expressions, provided by customers as a reiteration of an element of an English compound such as 'apple pie' [ fatˁi:rit ʔabil bai 'an apple pie pie'], from the perspective of Relevance Theory (RT). Data was collected from 90 participants, divided into two groups: 40 native speaker informants recruited from various shopping malls, and 50 shop assistants in Amman, Jordan. The first group was interviewed, whereas the second group filled out a multiple-choice task aimed at identifying the type of expression they typically receive when taking orders from customers. The data analysis revealed that Arabic tautological expressions are more frequently used compared to other alternatives. Drawing on RT, we argue that Arabic tautological expressions function as an ostensive stimulus. We propose that tautological expressions, utilized within a code-switching context, function as a means of pragmatic enrichment. This occurs through the process of ad hoc construction, wherein speakers refine the originally encoded concept to convey corrective or contrasting meanings. Instead of lacking information, the use of tautological phrases can be seen as a pragmatic tactic to maximize relevance by minimizing cognitive effort, optimizing successful communication of the intended meaning, and reinforcing contextual effects. • Examining the use of Arabic tautology in English compounds provided by customers. • Arabic tautologies are preferred and more frequently used than alternatives. • Drawing on RT, Arabic tautological expressions function as an ostensive stimulus. • The use of tautology conveys corrective or contrastive meanings via ad hoc concept construction. • The use of tautological phrases can be seen as a pragmatic tactic. [ABSTRACT FROM AUTHOR]

Copyright of Dirasat: Educational Sciences is the property of University of Jordan and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pretrained language models have achieved great success in various natural language understanding (NLU) tasks due to their capacity to capture deep contextualized information in text using pretraining on large-scale corpora. Tokenization plays a significant role in the process of lexical analysis. Tokens become the input for other natural language processing (NLP) tasks, like semantic parsing and language modeling. However, there is a lack of research on the evaluation of the impact of tokenization on the Arabic language model. Therefore, this study aims to address this gap in the literature by evaluating the performance of various tokenizers on Arabic large language models (LLMs). In this paper, we analyze the differences between WordPiece, SentencePiece, and BBPE tokenizers by pretraining three BERT models using each tokenizer while measuring the performance of each model on seven different NLP tasks using 29 different datasets. Overall, the model pretrained with text tokenized using the SentencePiece tokenizer significantly outperforms the other two models that utilize WordPiece and BBPE tokenizers. The results of this paper will assist researchers in developing better models, making better decisions in selecting the best tokenizers, improving feature engineering, and making models more efficient, thus ultimately leading to advancements in various NLP applications.

Ambiguity in some syntactic structures of the same language has always posed problems to the human translator and to machine translation. These problems become more complex for the Machine Translation of genetically unrelated languages such as Arabic, English and French. Arabic Lexical ambiguity in Natural Language Processing (NLP) also poses problems when the semantic fields of Arabic words differ from those of English for instance. This often occurs when two or more words from Arabic equate to a single word in English. Semantic gaps between the two languages are also a source of ambiguity in Natural Language Processing. We shall deal with some cases of ambiguity in machine translation from Arabic to English and French and vice versa. The questions addressed in this paper relate to segmentation, determination /non-determination, coordination and the issue of the word as a meaningful and functional unit. Some aspects of the segmentation of constituents into grammatical categories and their comparison with structures of Arabic English and French are addressed in this paper. [ABSTRACT FROM AUTHOR]

Deaf-mute individuals encounter substantial difficulties in their daily lives due to communication impediments. These individuals may encounter difficulties in social contact, communication, and capacity to acquire knowledge and engage in employment. Recent studies have contributed to decreasing the gap in communication between deaf-mute people and normal people by studying sign language interpretation. In this paper, a real-time Arabic avatar system is created to help deaf-mute people communicate with other people. The system translates text or spoken input into Arabic Sign Language (ArSL) movements that the avatar makes using deep-learning-based translation. The dynamic generation of the avatar movements allows smooth and organic real-time communication. In order to improve the precision and effectiveness of ArSL translation, this study depends on a state-of-the-art deep learning model, which makes use of YOLOv8, to recognize and interpret sign language gestures in realtime. The avatar is trained on three diverse datasets of Arabic sign language images, namely Sign-language-detection Image (SLDI), Arabic Sign Language (ArSL), and RGB Arabic Alphabet Sign Language (AASL), enabling it to accurately capture the nuances and variations of hand movements. The best recognition accuracy of the suggested approach was 99.4% on the AASL dataset. The experimental results of the suggested approach demonstrate that deaf-mute people will be able to communicate with others in Arabic-speaking communities more effectively and easily. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) substantially contributes to poor functional outcomes, loss in productivity, and poor health-related quality of life (HRQoL). Despite the existence of various scales, there is a notable gap in existing HRQoL reviews with regard to the availability of Arabic validated scales. As a response to this gap, the aim of our scoping review is to identify validated scales, focusing on their psychometric validation procedures, to contribute valuable insights to the understanding of HRQoL among the Arabic-speaking people with PD. Methods: A scoping review was conducted at the end of December 2022, using the Medline and Embase databases. The focus of this review was on examining the psychometric properties and validation procedures of included scales. Articles were included in the full-text screening process if they focused on people with PD of any age, included a scale measuring HRQoL in Arabic, and were written in English, French, or Arabic. Results: After applying inclusion/exclusion criteria, 10 studies were selected to analyze HRQoL scales validated in people with PD. However, the PDQ-39 is the only HRQol PD specific scales validated in the Arabic language. Five studies validated in people with PD were identified in the context of instrument validation (3 generic, 1 specific validated in 2 studies). Conclusion: There are several HRQoL measurement scales for people with PD. However, only one specific HRQoL instrument has been validated in Arabic for people with PD. For the remaining instruments identified they were just used in people with PD without being validated in this population. [ABSTRACT FROM AUTHOR]

Learning to write the Arabic alphabet is crucial for Arab children's cognitive development, enhancing their memory and retention skills. However, the lack of Arabic language educational applications may hamper the effectiveness of their learning experience. To bridge this gap, SamAbjd was developed, an interactive web application that leverages deep learning techniques, including air-writing recognition, to teach Arabic letters. SamAbjd was tailored to user needs through extensive surveys conducted with mothers and teachers, and a comprehensive literature review was performed to identify effective teaching methods and models. The development process involved gathering data from three publicly available datasets, culminating in a collection of 31,349 annotated images of handwritten Arabic letters. To enhance the dataset's quality, data preprocessing techniques were applied, such as image denoising, grayscale conversion, and data augmentation. Two models were experimented with using a convolution neural network (CNN) and Visual Geometry Group (VGG16) to evaluate their effectiveness in recognizing air-written Arabic characters. Among the CNN models tested, the standout performer was a seven-layer model without dropout, which achieved a high testing accuracy of 96.40%. This model also demonstrated impressive precision and F1-score, both around 96.44% and 96.43%, respectively, indicating successful fitting without overfitting. The web application, built using Flask and PyCharm, offers a robust and user-friendly interface. By incorporating deep learning techniques and user feedback, the web application meets educational needs effectively. [ABSTRACT FROM AUTHOR]

Background: Sexual and reproductive empowerment (SRE) is an important determinant of women's and girls' health yet measuring it is complex due to cultural and domain-specific variations. This study describes the process of adapting an SRE scale consisting of four domains (self-efficacy; future orientation; social support; and safety) and testing its psychometric properties among Arabic speaking adolescent girls in Lebanon. Methods: An SRE scale developed in a Western context was adapted in four steps: (1) reviewing the scale and selecting culturally appropriate domains for translation to standard Arabic; (2) conducting cognitive interviews with 30 11-17-year-old adolescent girls in Lebanon; (3) administering the scale to 339 refugee adolescent girls who participated in an early marriage intervention; and (4) conducting confirmatory factor analysis (CFA) on the data to assess the scale's psychometric properties. Results: The original model for the 13-item, four-domain adapted scale demonstrated poor fit in CFA. After iteratively removing two items, scale properties were improved, albeit were not optimal. The validity and reliability results for the self-efficacy domain were acceptable. Cognitive interview data revealed that Arab adolescent girls understood self-efficacy in relational terms, recognizing that autonomous decision-making is not necessarily favored but is influenced by parents and family. Conclusions: This study presents an effort to customize an SRE scale for use in studies on the health of adolescent girls in an Arab cultural context. Findings from cognitive interviews highlight the importance of taking into consideration relationality in adolescent sexual and reproductive decision-making. The self-efficacy domain in the adapted scale demonstrates acceptable psychometric properties and is recommended for use in health studies to capture SRE. [ABSTRACT FROM AUTHOR]

This study focuses on the principal stylistic characteristics of metrical formation and rhyme in the poetry collection of Taysīr Subūl Aḥzān Ṣaḥrāwiyyah ‘Desert Sorrows’. It explores the impact of traditional Arabic metrical forms on articulating the poet's real-life and psychological experiences. The research also delves into the importance of rhyme in fostering a unified emotional flow, maintaining the continuity of events, and culminating the poet's conceptual thoughts. The study concludes that Subūl's selection of classical Arabic meters (Buhur) and their metrical variations significantly contribute to the freedom and fluidity of his expression, enriching the rhythmic and semantic depth of his poetry. The varied application of softened rhyme schemes emerges as a prominent stylistic feature, encouraging readers to ponder over the implications and meanings of his poetic lines. [ABSTRACT FROM AUTHOR]

Text localization and recognition from natural scene images has gained a lot of attention recently due to its crucial role in various applications, such as autonomous driving and intelligent navigation. However, two significant gaps exist in this area: (1) prior research has primarily focused on recognizing English text, whereas Arabic text has been underrepresented, and (2) most prior research has adopted separate approaches for scene text localization and recognition, as opposed to one integrated framework. To address these gaps, we propose a novel bilingual end-to-end approach that localizes and recognizes both Arabic and English text within a single natural scene image. Specifically, our approach utilizes pre-trained CNN models (ResNet and EfficientNetV2) with kernel representation for localization text and RNN models (LSTM and BiLSTM) with an attention mechanism for text recognition. In addition, the AraElectra Arabic language model was incorporated to enhance Arabic text recognition. Experimental results on the EvArest, ICDAR2017, and ICDAR2019 datasets demonstrated that our model not only achieves superior performance in recognizing horizontally oriented text but also in recognizing multi-oriented and curved Arabic and English text in natural scene images. [ABSTRACT FROM AUTHOR]

This study investigates the phenomenon of “car embodiment”, where humans and machines are conceptualized as a hybrid creature in everyday language. Drawing on Langacker's (2008) theory of cognitive linguistics, the author analyzed natural examples of car embodiment metaphors posted online by Modern Standard Arabic (MSA) users. Findings of the current study revealed that actions and states (46%) were more frequently embodied than body parts (16%) in these metaphors. This suggests that the conceptual blending of humans and machines is primarily driven by shared functional and experiential features rather than physical similarities. This study contributes to the understanding of conceptual embodiment in the context of human-machine interaction and highlights the potential of online data for exploring linguistic creativity. [ABSTRACT FROM AUTHOR]

This study investigates the means to translate features of women’s language in Ibrahim Aslan’s novel Nile Sparrows from Arabic into English. Selected Arabic and English excerpts are placed in two questionnaires for native speakers of the two languages to decide whether the excerpts reflect features of women’s language. While responses to the Arabic questionnaire showed that the excerpts were brimful with features of women’s language, responses to the English questionnaire showed the neutrality of the translations. Eight selected examples were classified into three categories and analyzed using Reiss’ (2000) instruction criteria in light of Lakoff’s (1973) framework of the features of women’s language. The study found that reproducing the features of women’s language in another language may require sacrificing the lexical equivalence for stylistic equivalence based on how the translator settles the conflict between formal and functional equivalences. The study maintains that no one solution fits all when translating women’s language. Determinants of the translation decision depend on several factors, such as the nature of the target language, language level, ethnicity, geographic area, and topic [ABSTRACT FROM AUTHOR]

Nowadays, one of the most common problems faced by Twitter (also known as X) users, including individuals as well as organizations, is dealing with spam tweets. The problem continues to proliferate due to the increasing popularity and number of users of social media platforms. Due to this overwhelming interest, spammers can post texts, images, and videos containing suspicious links that can be used to spread viruses, rumors, negative marketing, and sarcasm, and potentially hack the user's information. Spam detection is among the hottest research areas in natural language processing (NLP) and cybersecurity. Several studies have been conducted in this regard, but they mainly focus on the English language. However, Arabic tweet spam detection still has a long way to go, especially emphasizing the diverse dialects other than modern standard Arabic (MSA), since, in the tweets, the standard dialect is seldom used. The situation demands an automated, robust, and efficient Arabic spam tweet detection approach. To address the issue, in this research, various machine learning and deep learning models have been investigated to detect spam tweets in Arabic, including Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB) and Long-Short Term Memory (LSTM). In this regard, we have focused on the words as well as the meaning of the tweet text. Upon several experiments, the proposed models have produced promising results in contrast to the previous approaches for the same and diverse datasets. The results showed that the RF classifier achieved 96.78% and the LSTM classifier achieved 94.56%, followed by the SVM classifier that achieved 82% accuracy. Further, in terms of F1-score, there is an improvement of 21.38%, 19.16% and 5.2% using RF, LSTM and SVM classifiers compared to the schemes with same dataset. [ABSTRACT FROM AUTHOR]

This research explores the language attitudes of second-generation Arabic speakers in Italy, examining their perspectives on both Italian and Arabic. The study assesses these attitudes within the complex sociolinguistic environment of Arabic, which is heavily influenced by a diglossic view between Standard Arabic and Arabic dialects. The findings highlight nuanced attitudes toward Italian, Standard Arabic, and Arabic dialects, influenced by factors such as social integration, communicative utility, and cultural identity. Italian is perceived as a tool for social advancement and integration. In contrast, Arabic dialects are essential for maintaining cultural and familial ties, yet they often face marginalization in formal education settings and encounter social stigma. Conversely, Standard Arabic is esteemed in formal and religious settings despite its limited everyday use. This analysis reveals a dynamic interplay of attitudinal responses to these languages, illustrating a rich mosaic of multilingual and multicultural identities. The results call for policies that acknowledge and promote linguistic diversity in Italy, aiming to enhance social integration and protect linguistic rights. These policies should include educational reforms that treat Standard Arabic and Arabic dialects equitably, supporting their role in fostering inclusive and comprehensive linguistic-cultural integration. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Community Service & Empowerment is the property of Journal of Community Service & Empowerment and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Background The clinical learning environment (CLE) plays a crucial role in shaping the learning experiences and professional development of medical professionals. Understanding and optimising this environment is essential for improving doctors’ knowledge acquisition, clinical skills, and overall well-being. The development of the Postgraduate Hospital Educational Environment Measure (PHEEM) and its translation to numerous languages has been a milestone in clinical education. Even though PHEEM was recently translated into Arabic, its psychometric properties in this form remain unevaluated. Therefore, this study aims to conduct a comprehensive psychometric analysis of the Arabic version of the PHEEM questionnaire. Methods This is a cross-sectional questionnaire survey validation study. The defined population were medical residents in Damascus, Syria. A paper-based survey as well as an online-based one were conducted using several non-probability sampling methods namely, convenience, river and, snowball sampling between June 15, 2023, and June 21, 2023. Both exploratory (EFA) and confirmatory (CFA) factor analyses were conducted. Several psychometric criteria were applied including scree plot, eigenvalue > 1.5 and the ‘proportion of variance accounted for’ criterion. Results A total of 543 participants completed the questionnaire (56.9% female). Kaiser-Meyer-Olkin measure for sample adequacy was high (0.937) and the P-value for Bartlett’s test was 0.7. Discussion The Arabic PHEEM inventory demonstrated satisfactory psychometric properties. The extracted domains are of theoretical relevance to the psychosocial-material conceptual framework for learning environment. Nonetheless, this validation was performed in the Syrian context; therefore, future studies in other Arabic countries are recommended to support the applicability of Arabic PHEEM in the wide Arab World.

Background: The Arab world is one of the global regions the most directly concerned by, and suffering from climate change's adverse consequences. As such, there appears to be a strong need for an understanding of how Arab people may emotionally respond to climate change. Providing valid and reliable measures of climate change anxiety (CCA) can help gain a clear overview of the situation in Arab countries, and allow to intervene timely and effectively to mitigate any adverse effects on Arab people's mental health. To this end, the present study sought to validate the Arabic language version of the Climate Change Anxiety Scale (CCAS) in a sample of native Arabic-speaking adults from the general population of Lebanon. Methods: This study adopted a cross-sectional approach and enrolled 763 adults between July and September 2023. Results: A confirmatory analysis of the one-factor model showed poor fit indices as follows: CFI = 0.90, GFI = 0.83, SRMR = 0.048 and RMSEA 0.131 [90% CI 0.123, 0.138). The two-factor model showed a satisfactory fit with a high CFI of and a GFI of 0.91 and a SRMR of 0.04 and RMSEA of 0.05 [90% CI 0.04, 0.06]. Both McDonald's omega and Cronbach alpha values were high for the overall CCAS score (α = 0.96 and ω = 0.96) in the whole sample. Configural, metric and scalar invariance across gender was demonstrated. No significant difference was found between males and females in terms of total CCAS scores (24.53 ± 10.59 vs. 26.03 ± 11.17, t(761) = -1.82, p =.069). Higher CCA, functional impairment and cognitive impairment scores were significantly associated with higher depression, anxiety and stress. Conclusion: The reliability and validity of the CCAS in its Arabic version were proven. The availability of this self-report measure could offer a chance to assess CCA among Adults speaking Arabic, and to spread its future use for screening and research purposes. [ABSTRACT FROM AUTHOR]

Copyright of Humanities & Educational Sciences Journal is the property of Humanities & Educational Sciences Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Social media platforms have become essential for disseminating news and expressing individual sentiments on various life topics. Arabic, widely used in the Middle East, presents unique challenges for sentiment analysis due to its complexity and multiple dialects. Motivated by the need to address these challenges, this article develops methods to overcome the lack of topic-based labeling techniques, compares different approaches for preparing extensive, annotated datasets, and analyzes the efficacy of machine learning (ML), deep learning (DL), and large language models (LLMs) in classifying Arabic textual data. Our research utilizes the topic-modeling technique to build a topic-based sentiment dataset of Arabic texts aimed at enhancing our understanding and processing capabilities. We present a comprehensive evaluation of dataset balancing techniques, including under-sampling, over-sampling, and using imbalanced datasets, providing insights into how these approaches impact classification outcomes. Additionally, we explore the influence of dataset sizes on the performance of various ML models, highlighting the importance of dataset scale in developing effective Arabic NLP applications. A further focus of our study is the comparative analysis of generative artificial intelligence (AI) models, including the emerging ChatGPT LLM, assessing their effectiveness in managing the complexities of Arabic language classification tasks. Our results show that support vector machines (SVM) achieved the highest performance, with F1-scores of 0.97 and 0.96 in classifying sentiment and topic, respectively, in Arabic tweets. This research not only benchmarks existing methodologies but also paves the way for more nuanced and robust models in the future, enhancing the application of generative AI in Arabic topic-based sentiment analysis. [ABSTRACT FROM AUTHOR]

Despite the increasing demand for learning foreign languages such as Arabic, approaches to teaching this language remain under-explored. The increasing complexity of classrooms renders the task of ensuring that learners with diverse backgrounds and experiences attain the stated objectives, challenging. To address this challenge, this study proposes the 3Cs approach, which combines communicative language teaching, collaborative learning and social constructivist theory, to improve the teaching and learning of Arabic. This approach integrates communicative techniques based on social constructivist theory and is implemented through the acquisition of shared knowledge of the environment. The 3Cs-based approach, which promotes students' active involvement, has the potential to facilitate comprehensive learning and real-world applications, offering new opportunities for both teachers and students to improve outcomes and address classroom difficulties. [ABSTRACT FROM AUTHOR]