Sultan Almujaiwel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sultan Almujaiwel has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Abdulmohsen Al-Thubaity
King Abdulaziz City for Science and Technology
1 shared publication - Damith Premasiri
Lancaster University, Lancaster, United Kingdom
1 shared publication - Dinesh Kumar Sah
Division of Networked and Embedded Systems, Mlardalen University, Vsters, Sweden
1 shared publication - Ibrahim Alrashdi
Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka, Saudi Arabia
1 shared publication - Korhan Cengiz
College of Computing and Intelligent Systems, University of Khorfakkan, Sharjah, United Arab Emirates
1 shared publication - Mahmoud El-Haj
Lancaster University
1 shared publication
Latest Publications
- Open Access
- 17 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 24 (11) , 1-21
Complex Concept-Based Readability Estimation from Arabic Curriculum
This article presents an approach to readability estimation that focuses on conceptual rather than linguistic complexity, using the extensive SaudiTextBooks textbooks. We introduce DARES 2.0 , an enhanced concept-based readability training dataset designed to estimate the readability of Saudi educational texts. Building on DARES 1.0, DARES 2.0 extends the scope of conceptual complexity by replacing repetitive concepts and manually revising the input features with unique terms and their surrounding contexts from the SaudiTextBooks, spanning grades 1 to 12. The refined DARES 2.0 is employed to fine-tune pre-trained transformer models, including XLM-R Base, mBERT, AraELECTRA, AraBERTv2, and CAMeLBERTmix. The findings suggest that both the dataset and experimental setup require further development to ensure a larger, higher-quality dataset and to support more extensive fine-tuning experiments, in addition to exploring transfer learning from other languages and enhancing the diversity and richness of Arabic concepts. These developments pave the way for further advancements in concept-based readability estimation in educational contexts in future work.
- 17 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 24 (11) , 1-21
Open AccessComplex Concept-Based Readability Estimation from Arabic Curriculum
This article presents an approach to readability estimation that focuses on conceptual rather than linguistic complexity, using the extensive SaudiTextBooks textbooks. We introduce DARES 2.0 , an enhanced concept-based readability training dataset designed to estimate the readability of Saudi educational texts. Building on DARES 1.0, DARES 2.0 extends the scope of conceptual complexity by replacing repetitive concepts and manually revising the input features with unique terms and their surrounding contexts from the SaudiTextBooks, spanning grades 1 to 12. The refined DARES 2.0 is employed to fine-tune pre-trained transformer models, including XLM-R Base, mBERT, AraELECTRA, AraBERTv2, and CAMeLBERTmix. The findings suggest that both the dataset and experimental setup require further development to ensure a larger, higher-quality dataset and to support more extensive fine-tuning experiments, in addition to exploring transfer learning from other languages and enhancing the diversity and richness of Arabic concepts. These developments pave the way for further advancements in concept-based readability estimation in educational contexts in future work.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 34900-34909
Energy-Efficient Task Allocation for IIoT Deep Learning Applications: An Embedded Edge Clusters Solution
Integration of deep learning-based edge computing into industrial processes has enabled intelligent automation in the Industrial Internet of Things (IIoT). However, the deployment of deep learning inference models in embedded edge clusters remains a challenge due to energy constraints, communication latency, and computational limitations. This article proposes an energy-aware task allocation framework for optimizing deep learning inference in IIoT environments utilizing a Embedded cluster with both Wi-Fi and Ethernet-based communication setups. We have implemented and evaluated the performance of four classical deep learning models (MobileNet single shot detector (SSD), Tiny YOLO, EfficientDet Lite, and Faster R-CNN) on the edge cluster and analyze their execution time, energy consumption, and network efficiency. The framework provides a scalable and energy-efficient solution for deploying deep learning inference on resource-constrained edge computing platforms. The is ongoing development for the Embedded-Edge test beds and Future work will explore heterogeneous edge device integration and 5G-enabled computing for further performance enhancements. Experimental results demonstrate that Ethernet-based communication improves task execution speed by 15%–20% and reduces energy consumption by 12%–18% compared to Wi-Fi. Additionally, a fault-tolerant task reallocation mechanism ensures uninterrupted operation in case of node failures. The findings suggest that efficient task scheduling and network optimization strategies can significantly enhance the real-time processing capability of IIoT applications on Embedded edge also.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 34900-34909
Energy-Efficient Task Allocation for IIoT Deep Learning Applications: An Embedded Edge Clusters Solution
Integration of deep learning-based edge computing into industrial processes has enabled intelligent automation in the Industrial Internet of Things (IIoT). However, the deployment of deep learning inference models in embedded edge clusters remains a challenge due to energy constraints, communication latency, and computational limitations. This article proposes an energy-aware task allocation framework for optimizing deep learning inference in IIoT environments utilizing a Embedded cluster with both Wi-Fi and Ethernet-based communication setups. We have implemented and evaluated the performance of four classical deep learning models (MobileNet single shot detector (SSD), Tiny YOLO, EfficientDet Lite, and Faster R-CNN) on the edge cluster and analyze their execution time, energy consumption, and network efficiency. The framework provides a scalable and energy-efficient solution for deploying deep learning inference on resource-constrained edge computing platforms. The is ongoing development for the Embedded-Edge test beds and Future work will explore heterogeneous edge device integration and 5G-enabled computing for further performance enhancements. Experimental results demonstrate that Ethernet-based communication improves task execution speed by 15%–20% and reduces energy consumption by 12%–18% compared to Wi-Fi. Additionally, a fault-tolerant task reallocation mechanism ensures uninterrupted operation in case of node failures. The findings suggest that efficient task scheduling and network optimization strategies can significantly enhance the real-time processing capability of IIoT applications on Embedded edge also.
- Open Access
- 23 February 2023
- Published by MDPI AG in Social Sciences
- Vol. 12 (3) , 114
Computational Techniques for Analyzing Women’s Social Change in Saudi Newspapers
This study utilized computational techniques for a reliable analysis of discourse. These techniques were adopted to analyze the progress of Saudi social change in terms of women’s empowerment within the Saudi transformation program. The data from open source 2021–2022 Saudi newspaper archives were automatically crawled using cutting-edge computational techniques and structured according to the sections of the Saudi newspapers: front page, economy, international, sports, society, culture and religion. The analysis was based on computing the minimally uneven distribution of the relative frequencies of the occurrence of the central word (the Arabic forms of woman and women) from the years 2021 to 2022. This produced two samples of text data, each of which represented the respective years. Calculating the normalized and adjusted frequencies of the central word from each section in the data from each year was important to avoid unbalanced absolute frequencies in the qualitative analysis stage. In addition, dispersion measures showed that the amount of variance in terms of the lexical dispersion of the central word was not high. The observable facts from the quantitative analysis produced a more accurate observational sample of citations, which we qualitatively analyzed. The results of the latter showed a considerable ascending change in favor of empowering women as a consequence of Saudi Vision 2030.
- 23 February 2023
- Published by MDPI AG in Social Sciences
- Vol. 12 (3) , 114
Open AccessComputational Techniques for Analyzing Women’s Social Change in Saudi Newspapers
This study utilized computational techniques for a reliable analysis of discourse. These techniques were adopted to analyze the progress of Saudi social change in terms of women’s empowerment within the Saudi transformation program. The data from open source 2021–2022 Saudi newspaper archives were automatically crawled using cutting-edge computational techniques and structured according to the sections of the Saudi newspapers: front page, economy, international, sports, society, culture and religion. The analysis was based on computing the minimally uneven distribution of the relative frequencies of the occurrence of the central word (the Arabic forms of woman and women) from the years 2021 to 2022. This produced two samples of text data, each of which represented the respective years. Calculating the normalized and adjusted frequencies of the central word from each section in the data from each year was important to avoid unbalanced absolute frequencies in the qualitative analysis stage. In addition, dispersion measures showed that the amount of variance in terms of the lexical dispersion of the central word was not high. The observable facts from the quantitative analysis produced a more accurate observational sample of citations, which we qualitatively analyzed. The results of the latter showed a considerable ascending change in favor of empowering women as a consequence of Saudi Vision 2030.
- 1 August 2018
- Published by Edinburgh University Press in Corpora
- Vol. 13 (2) , 135-168
Explaining the complexities of cross-linguistic features using comparable Arabic and English corpora
The aim of this paper was to conduct a critical inquiry into the status of equivalence in a given context in a bilingual lexicographical work and English–Arabic comparable corpora. This was intended to show the degree of accuracy which old-fashioned approaches and comparable corpora-based ones achieve. The investigation that was launched to demonstrate the degree of accuracy is based on the case of the entries questionnaire and survey, and their Arabic equivalents, al-ʾistiftāʾ and al-ʾistibyān. As these entries and equivalents have been given interchangeable senses in the lexicographical work, the comparable corpora have given evidence of clear-cut distinctions between them. The comparable English–Arabic corpora used in the case study is the Bank of English (WordbanksOnline) and the following three Arabic corpora: Arabic Internet Corpus, Arabic Wikipedia and arabiCorpus. The large-scale comparable English–Arabic corpora-based approach to the intended entries and equivalents has shown the importance of such a method. In spite of comparability between English and Arabic still being underdeveloped, the use of comparable corpora in this paper was identified by adopting the following criteria: sampling frame, genres, proportions and years of natural texts. Each entry with each equivalent were examined in their expanded concordance lines, with a span of about ten n-grams, in order to sketch their contextual senses. This has helped to criticise the contextually inappropriate equivalence of the intended entries. Such an analysis has implied that sketching contexts conveyed by large-scale source and target corpora can help to enhance the reliability of equivalence divisions.
- 1 August 2018
- Published by Edinburgh University Press in Corpora
- Vol. 13 (2) , 135-168
Explaining the complexities of cross-linguistic features using comparable Arabic and English corpora
The aim of this paper was to conduct a critical inquiry into the status of equivalence in a given context in a bilingual lexicographical work and English–Arabic comparable corpora. This was intended to show the degree of accuracy which old-fashioned approaches and comparable corpora-based ones achieve. The investigation that was launched to demonstrate the degree of accuracy is based on the case of the entries questionnaire and survey, and their Arabic equivalents, al-ʾistiftāʾ and al-ʾistibyān. As these entries and equivalents have been given interchangeable senses in the lexicographical work, the comparable corpora have given evidence of clear-cut distinctions between them. The comparable English–Arabic corpora used in the case study is the Bank of English (WordbanksOnline) and the following three Arabic corpora: Arabic Internet Corpus, Arabic Wikipedia and arabiCorpus. The large-scale comparable English–Arabic corpora-based approach to the intended entries and equivalents has shown the importance of such a method. In spite of comparability between English and Arabic still being underdeveloped, the use of comparable corpora in this paper was identified by adopting the following criteria: sampling frame, genres, proportions and years of natural texts. Each entry with each equivalent were examined in their expanded concordance lines, with a span of about ten n-grams, in order to sketch their contextual senses. This has helped to criticise the contextually inappropriate equivalence of the intended entries. Such an analysis has implied that sketching contexts conveyed by large-scale source and target corpora can help to enhance the reliability of equivalence divisions.
- 30 June 2018
- Published by The Journal of Asia TEFL in The Journal of AsiaTEFL
- Vol. 15 (2) , 414-428
Culture and Interculture in Saudi EFL Textbooks : A Corpus-Based Analysis
This paper combines corpus processing tools to investigate the cultural elements of Saudi education of English as a foreign language (EFL) textbooks. The latest Saudi EFL textbooks (2016 onwards) are available in researchable PDF formats. This helps process them through corpus search software tools. The method adopted is based on analysing 20 cultural topics (nodes), namely climate, clothing, eating, education, family life, geography, history, holidays, humour, language, leisure, meeting people, currency, pets, population, religions, social occasions, sports, transportation and vacations. Function words, verbs, adjectives and punctuation were removed from the files of Saudi EFL textbooks. This guarantees searching for only cultural content words that are associated with the 20 selected cultural topics. The processing of the associations helps identify the type of culture quantitatively: local culture, target culture, and interculture. The results show that local Arabic cultural words are more frequent than target English cultural words, and the latter is more frequent than the intercultural words. This highlights a lack of intercultural examples in the whole corpus of Saudi EFL textbooks. This implies that a reconsideration of intercultural examples is needed for developing English language teaching materials. This is due largely to English being widely used as a lingua franca.
- 30 June 2018
- Published by The Journal of Asia TEFL in The Journal of AsiaTEFL
- Vol. 15 (2) , 414-428
Culture and Interculture in Saudi EFL Textbooks : A Corpus-Based Analysis
This paper combines corpus processing tools to investigate the cultural elements of Saudi education of English as a foreign language (EFL) textbooks. The latest Saudi EFL textbooks (2016 onwards) are available in researchable PDF formats. This helps process them through corpus search software tools. The method adopted is based on analysing 20 cultural topics (nodes), namely climate, clothing, eating, education, family life, geography, history, holidays, humour, language, leisure, meeting people, currency, pets, population, religions, social occasions, sports, transportation and vacations. Function words, verbs, adjectives and punctuation were removed from the files of Saudi EFL textbooks. This guarantees searching for only cultural content words that are associated with the 20 selected cultural topics. The processing of the associations helps identify the type of culture quantitatively: local culture, target culture, and interculture. The results show that local Arabic cultural words are more frequent than target English cultural words, and the latter is more frequent than the intercultural words. This highlights a lack of intercultural examples in the whole corpus of Saudi EFL textbooks. This implies that a reconsideration of intercultural examples is needed for developing English language teaching materials. This is due largely to English being widely used as a lingua franca.
- Open Access
- 2 May 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Integrating NLP with Corpus Linguistics and Vice Versa
- 2 May 2018
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessIntegrating NLP with Corpus Linguistics and Vice Versa
- 14 July 2017
- Published by Taylor & Francis in Journal of Quantitative Linguistics
- Vol. 25 (2) , 122-141
A quantitative Inquiry into the Keywords between Primary and Reference Arabic Corpora
- 14 July 2017
- Published by Taylor & Francis in Journal of Quantitative Linguistics
- Vol. 25 (2) , 122-141
A quantitative Inquiry into the Keywords between Primary and Reference Arabic Corpora
- 4 June 2017
- Published by SAGE Publications in Discourse & Communication
- Vol. 11 (5) , 441-466
Discursive patterns of anti-feminism and pro-feminism in Arabic newspapers of the KACST corpus
This article presents the results of an analysis of the large-scale processed texts of Arabic newspapers in the King Abdulaziz City for Science and Technology (KACST) Arabic Corpus Project. I adopted methods modified from the Biber Connor Upton Approach to retrieve the expanded concordances of the lexical units almarᵓa (woman) and alnisāᵓ (women) from the corpus. The extracted text reveals the discursive patterns regarding a number of topics which are discussed in Arabic newspapers, namely, socio-culture (social practices) and eco-politics. The results of the study show how and why topics related to Arab women are discursively constructed, revealing negative patterns with regard to the topics discrimination, the veil, sports, male guardianship, driving, pro-divorce settlements and municipal elections, and positive patterns concerning the topics marital status, violence, education, travel, sexual harassment, the removal of male guardianship, employment, ministerial election and political participation. The specific case of the topic (un)veil is subsequently analysed in more detail and the results reveal that the topic is associated with negative patterns within a wider socio-cultural discourse.
- 4 June 2017
- Published by SAGE Publications in Discourse & Communication
- Vol. 11 (5) , 441-466
Discursive patterns of anti-feminism and pro-feminism in Arabic newspapers of the KACST corpus
This article presents the results of an analysis of the large-scale processed texts of Arabic newspapers in the King Abdulaziz City for Science and Technology (KACST) Arabic Corpus Project. I adopted methods modified from the Biber Connor Upton Approach to retrieve the expanded concordances of the lexical units almarᵓa (woman) and alnisāᵓ (women) from the corpus. The extracted text reveals the discursive patterns regarding a number of topics which are discussed in Arabic newspapers, namely, socio-culture (social practices) and eco-politics. The results of the study show how and why topics related to Arab women are discursively constructed, revealing negative patterns with regard to the topics discrimination, the veil, sports, male guardianship, driving, pro-divorce settlements and municipal elections, and positive patterns concerning the topics marital status, violence, education, travel, sexual harassment, the removal of male guardianship, employment, ministerial election and political participation. The specific case of the topic (un)veil is subsequently analysed in more detail and the results reveal that the topic is associated with negative patterns within a wider socio-cultural discourse.
- 12 May 2017
- Published by Walter de Gruyter GmbH in Corpus Linguistics and Linguistic Theory
- Vol. 15 (2) , 267-296
Grammatical construction of function words between old and modern written Arabic: A corpus-based analysis
This paper argues that Arabic function words (FWs) vary in usage between old and modern Arabic, thus prompting an experimental investigation into their changeability. This investigation is carried out by testing classical Arabic (CA) in Arabic heritage language (AHL) texts – those labeled as archistratum – and the modern standard Arabic (MSA) of Arabic newspaper texts (ANT), each group of which contains randomly collected 5 million (M) word texts. The linguistic theory of the grammar of Arabic FWs is explained through the differences between CA and MSA, despite Arabic FW changes and the unlearnability and/or unusability of some FW constructions between in these two eras of Arabic usage. The dispersion/distribution of the construction grammar (CxG) of FWs and the number (n) of word attractions/repulsions between the two distinct eras is explored using the very latest and most sophisticated Arabic corpus processing tools, and Sketch Engine’sSkeEn gramrelsoperators. The analysis of a 5 M word corpus from each era of Arabic serves to prove the non-existence of rigorous Arabic CxG. The approach in this study adopts a technique which, by contrasting AHL with ANT, relies on analyzing the frequency distributions of FWs, the co-occurrences of FWs in a span of 2n-grams collocational patterning, and some cases of FW usage changes in terms of lexical cognition (FW grammatical relationships). The results show that the frequencies of FWs, in addition to the case studies, are not the same, and this implies that FWs and their associations with the main part of speech class in a fusion language like Arabic have grammatically changed in MSA. Their constructional changes are neglected in Arabic grammar.
- 12 May 2017
- Published by Walter de Gruyter GmbH in Corpus Linguistics and Linguistic Theory
- Vol. 15 (2) , 267-296
Grammatical construction of function words between old and modern written Arabic: A corpus-based analysis
This paper argues that Arabic function words (FWs) vary in usage between old and modern Arabic, thus prompting an experimental investigation into their changeability. This investigation is carried out by testing classical Arabic (CA) in Arabic heritage language (AHL) texts – those labeled as archistratum – and the modern standard Arabic (MSA) of Arabic newspaper texts (ANT), each group of which contains randomly collected 5 million (M) word texts. The linguistic theory of the grammar of Arabic FWs is explained through the differences between CA and MSA, despite Arabic FW changes and the unlearnability and/or unusability of some FW constructions between in these two eras of Arabic usage. The dispersion/distribution of the construction grammar (CxG) of FWs and the number (n) of word attractions/repulsions between the two distinct eras is explored using the very latest and most sophisticated Arabic corpus processing tools, and Sketch Engine’sSkeEn gramrelsoperators. The analysis of a 5 M word corpus from each era of Arabic serves to prove the non-existence of rigorous Arabic CxG. The approach in this study adopts a technique which, by contrasting AHL with ANT, relies on analyzing the frequency distributions of FWs, the co-occurrences of FWs in a span of 2n-grams collocational patterning, and some cases of FW usage changes in terms of lexical cognition (FW grammatical relationships). The results show that the frequencies of FWs, in addition to the case studies, are not the same, and this implies that FWs and their associations with the main part of speech class in a fusion language like Arabic have grammatically changed in MSA. Their constructional changes are neglected in Arabic grammar.