Search

This paper focuses on exploring the differences in inquiries made by men and women within a religious context. Additionally, we aim to ascertain whether it’s feasible to forecast the popularity of answers and the factors contributing to their popularity. To achieve this, we compile a new dataset comprising 40,000 question-answer pairs categorized by gender and popularity. These are sourced from online question-and-answer platforms. Our methodology involves comprehensive experimental analysis, utilizing advanced Arabic text preprocessing alongside machine learning algorithms. We concentrate on two primary objectives: predicting the gender of the questioner and forecasting the popularity of answers. Furthermore, we delve into thematic variations based on gender and address pivotal research queries that offer new perspectives within this domain. These include investigating the differences between questions posed by women versus men, exploring the potential for automated classification of queries by gender, predicting the popularity of fatwas, and identifying the contributing factors to their popularity. Our experimental findings demonstrate a 98% accuracy in gender prediction, precise predictions of popularity with minimal margin for error, and the identification of topics and their associations that are more inclined towards either men or women. We intend to share both the dataset and the source code openly with the research community.

The electrical system performance can be improved considerably by controlling the reactive power flow in the system. The reactive power control can be achieved by optimal reactive power dispatch (ORPD) problem solution and optimal integration of the FACTS devices. With high penetration of renewable energy sources (RESs) and the load growth, the ORPD solution became a challenging and a complex task due to the stochastic nature of the RERs and the load growth. In this regard, the aim of this paper is to solve the stochastic optimal reactive power dispatch (SORPD) with optimal inclusion of PV units, wind turbines and the unified power flow controller (UPFC) under uncertainties of the load growth and the generated powers. An Adaptive Beluga Whale Optimization (ABWO) is proposed for solving the SORPD which is based on the Fitness-Distance Balance Selection (FDBS) strategy and the territorial solitary males' strategy of the Mountain Gazelle Optimizer. The proposed ABWO is tested on IEEE 30-bus system and a comparison with other optimization techniques for solving the ordinary ORPD is presented for validating the proposed ABWO. The obtained results reveal that the TEPL is reduced from 5.3168 MW to 3.97985 MW with optimal integration of the RERs and UPFC. Likewise, the TEVD is reduced from 0.1794p.u. to 0.10689p.u. and the TVSI is decreased from 0.1289p.u. to 0.0476p.u.

This study examined urban heat dynamics in 21 major Middle Eastern cities from 2003 to 2019. Changes in daytime and nighttime land surface temperature (LST) during summertime were assessed using the least squares regression model. The most pronounced increase in LST was found in Gulf and Arabian Peninsula cities, while higher altitude cities (e.g., Beirut and Sanaa) showed the least warming. The increase in nighttime LST was higher than daytime LST, especially in inland cities. Heat stress exposure was assessed using hot/cold spot categories. Over 11 million people in megacities are at risk of heat stress. Our findings show that most cities had significant day-night thermal risk distribution differences, with heat stress being more common in central urban areas at night and in urban periphery during daytime. City nighttime LST may serve as a more reliable indicator of anthropogenic climate change compared to daytime LST effects, which primarily result from physical factors such as the inflow of hot air from nearby deserts. Also, while built-up areas correlated with hot/cold spots in most cities, a complex relationship exists between vegetation and hot/cold spot patterns. Our study emphasizes well-informed urban planning and adaptable mitigation strategies to protect urban populations from heat stress.

Given a set of target language documents and their translators, the translator attribution task aims at identifying which translator translated which documents. The attribution and the identification of the translator’s style could contribute to fields including translation studies, digital humanities, and forensic linguistics. To conduct this investigation, firstly, we develop a new corpus containing the translations of world-famous books into Arabic. We then pre-process the books in our corpus which mainly involves cleaning irrelevant material, morphological segmentation analysis of words, and devocalization. After pre-processing the books, we propose to use 100 most frequent words and/or morphologically segmented function words as writing style markers of the translators (i.e. stylometric features) to differentiate between translations of different translators. After the completion of features extraction process, we applied several supervised and unsupervised machine-learning algorithms along with our novel cluster-to-author index to perform this task. We found that the translators are not invisible, and morphological analysis may not be more useful than just using the 100 most frequent words as features. The support vector machine linear kernel algorithm reported 99% classification accuracy. Similar findings were reported by the unsupervised machine-learning methods, namely, K-mean clustering and hierarchical clustering.

Biographical writing is one of the earliest and most extensive forms of Arabic literature. Some scholars tend to assume that classical Arabic biographies, widely known as Tarāǧim, arose in conjunction with the study of the reliability of the Hadith transmitters (the reciters of the Prophet Mohammad's sayings) which lead to a proliferation of biographical material collected and used to assess the transmitter's trustworthiness . However, a scrutiny of the well-known classical Arabic biographical dictionaries such as Siyaru 'A`lāmi an-Nubalā' `The Lives of the Noble Figures' for Adh-Dhahabī shows that they extend their entries to other classes of persons important to the development of particular fields such as Islamic jurisprudents, rulers, poets, philosophers or physicians. The main contribution of Arabic biographical dictionaries is the cumulative value of the thousands of life histories which construct a picture of the Islamic society in different eras. An Arabic biographical dictionary, therefore, is predominantly used by scholars to look up an eminent person's achievements and historical background. In this project, however, we explore Arabic biographies as a prosopography, rather than a biography in the strict sense. We introduce a novel method for a better understanding of Arabic biographical dictionaries by creating a network of relations among different persons. We utilise Natural Language Processing (NLP) tools to create a topological network from the unstructured data of 45,500 biographical entries collected from different dictionaries. We aim to illustrate how network analysis leveraged by NLP tools can provide scholars with innovative methods for discovering complex constellation of relations between prominent and non-prominent figures spanning over several eras and from different fields of knowledge. We also use graph visualisation as a means to effectively communicate and explore such complex constellations. Each network visualisation is purposefully de

There has not been any research that provides an evaluation of the linguistic features extracted from the matn (text) of a Hadith. Moreover, none of the fairly large corpora are publicly available as a benchmark corpus for Hadith authenticity, and there is a need to build a 'gold standard' corpus for good practices in Hadith authentication. We write a scraper in Python programming language and collect a corpus of 3,651 authentic prophetic traditions and 3,593 fake ones. We process the corpora with morphological segmentation and perform extensive experimental studies using a variety of machine learning algorithms, mainly through automatic machine learning, to distinguish between these two categories. With a feature set including words, morphological segments, characters, top N words, top N segments, function words, and several vocabulary richness features, we analyze the results in terms of both prediction and interpretability to explain which features are more characteristic of each class. Many experiments have produced good results and the highest accuracy (i.e. 78.28%) is achieved using word n-grams as features using the Multinomial Naive Bayes classifier. Our extensive experimental studies conclude that, at least for Digital Humanities, feature engineering may still be desirable due to the high interpretability of the features. The corpus and software (scripts) will be made publicly available to other researchers in an effort to promote progress and replicability.

Translation plays a key role in conveying the message from one Source Language (SL) to Target Language (TL). However, it does not necessarily refer to two different languages as translation is generally classified into three categories (intralingual, interlingual and intersemiotic). Among the existing translation methods, two methods are intensively being compared and debated over: semantic and communicative translation. While the former has a connection to literal and free translation, the latter has been recently and popularly recognized for its importance in the field of translation. The semantic approach tends to preserve the author’s language expression by giving utmost importance on its peculiar content and meaning. On the other hand, in the communicative approach, the translator has the freedom to remove obscurities, eliminate repetition and specify the general terms for the comprehension of the audience. Furthermore, translation is not as an easy task as it seems. Successful translation requires complicated multi-task practice that involves the application of various skills. Not to mention the impact of word concreteness and dominance on translation efficiency as well as the continuous improvement in proficiency that all bilinguals need to cope with. Although the two approaches function differently, there are some cases when the application of both methods is required. This is especially true in translating texts where both the “form” and “content” are equally important. In conclusion, the connection and the bond between culture and language cannot be underestimated as they are closely intertwined with each other. In the process of translation, where three main important players (author, translator and receiver) from various cultural backgrounds are involved, no matter how the mediator tries to translate the Source Language to Target Language (either semantically or communicatively), loss of message during the process is inevitable.

The primary purpose of this article is author verification of the Nahj Al-Balagha, a book attributed to Imam Ali and over which Sunni and Shi’i Muslims are proposing different theories. Given the morphologically complex nature of Arabic, we test whether morphological segmentation, applied to the book and works by the two authors suspected by Sunnis to have authored the texts, can be used for author verification of the Nahj Al-Balagha. Our findings indicate that morphological segmentation may lead to slightly better results than whole words and that regardless of the feature sets, the three sub-corpora cluster into three distinct groups using principal component analysis, hierarchical clustering, multi-dimensional scaling, and bootstrap consensus trees. Supervised classification methods such as Naive Bayes, Support Vector Machines, k Nearest Neighbours, Random Forests, AdaBoost, Bagging, and Decision Trees confirm the same results, which is a clear indication that (1) the book is internally consistent and can thus be attributed to a single person and (2) it was not authored by either of the suspected authors.

In the online world, Machine Translation (MT) systems are extensively used to translate User-Generated Text (UGT) such as reviews, tweets, and social media posts, where the main message is often the author's positive or negative attitude towards the topic of the text. However, MT systems still lack accuracy in some low-resource languages and sometimes make critical translation errors that completely flip the sentiment polarity of the target word or phrase and hence delivers a wrong affect message. This is particularly noticeable in texts that do not follow common lexico-grammatical standards such as the dialectical Arabic (DA) used on online platforms. In this research, we aim to improve the translation of sentiment in UGT written in the dialectical versions of the Arabic language to English. Given the scarcity of gold-standard parallel data for DA-EN in the UGT domain, we introduce a semi-supervised approach that exploits both monolingual and parallel data for training an NMT system initialised by a cross-lingual language model trained with supervised and unsupervised modeling objectives. We assess the accuracy of sentiment translation by our proposed system through a numerical 'sentiment-closeness' measure as well as human evaluation. We will show that our semi-supervised MT system can significantly help with correcting sentiment errors detected in the online translation of dialectical Arabic UGT., Comment: WANLP2022 at EMNLP 2022

In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source text, i.e. the author's sentiment. In the online world, MT systems are extensively used to translate User-Generated Content (UGC) such as reviews, tweets, and social media posts, where the main message is often the author's positive or negative attitude towards the topic of the text. It is important in such scenarios to accurately measure how far an MT system can be a reliable real-life utility in transferring the correct affect message. This paper tackles an under-recognised problem in the field of machine translation evaluation which is judging to what extent automatic metrics concur with the gold standard of human evaluation for a correct translation of sentiment. We evaluate the efficacy of conventional quality metrics in spotting a mistranslation of sentiment, especially when it is the sole error in the MT output. We propose a numerical `sentiment-closeness' measure appropriate for assessing the accuracy of a translated affect message in UGC text by an MT system. We will show that incorporating this sentiment-aware measure can significantly enhance the correlation of some available quality metrics with the human judgement of an accurate translation of sentiment., Comment: Accepted for RANLP (Recent Advances in Natural Language Processing) 2021

A Master of Science thesis in Civil Engineering by Mohamed Emad Ali entitled, “Strength of Concrete Produced with Recycled Materials”, submitted in December 2019. Thesis advisor is Dr. Sherif Yehia and thesis co-advisor is Dr. Farid Abed. Soft copy is available (Thesis, Approval Signatures, Completion Certificate, and AUS Archives Consent Form)., College of Engineering, Department of Civil Engineering

This study aims to analyze texts through analysis of invisible text, which includes many meanings, expressions and norms that can be accessed by symbolic behavior such as language, literature, and the arts. In recent decades, the rapid increase in the development and availability of resources and computational technology has led to an increase in the analysis of multimedia texts that appear in a range of disciplines in clouded in the above study the prevalence of contemporary digital media forms requires researchers to keep sociocultural developments. At this stage, multimedia studies are required as a kind of experimental text, Este estudio tiene como objetivo analizar los textos a través del análisis de texto invisible que incluye muchos significados, expresiones y normas a los que se puede acceder mediante un comportamiento simbólico como el lenguaje, la literatura y las artes. En las últimas décadas, el rápido aumento en el desarrollo y la disponibilidad de recursos y tecnología computacional ha llevado a un aumento en el análisis de textos multimedia que aparecen en una variedad de disciplinas en el estudio anterior, la prevalencia de las formas contemporáneas de medios digitales requiere investigadores que mantengan los desarrollos socioculturales. En esta etapa, se requieren estudios multimedia como una especie de texto experimental.

One very common type of fake news is satire which comes in a form of a news website or an online platform that parodies reputable real news agencies to create a sarcastic version of reality. This type of fake news is often disseminated by individuals on their online platforms as it has a much stronger effect in delivering criticism than through a straightforward message. However, when the satirical text is disseminated via social media without mention of its source, it can be mistaken for real news. This study conducts several exploratory analyses to identify the linguistic properties of Arabic fake news with satirical content. We exploit these features to build a number of machine learning models capable of identifying satirical fake news with an accuracy of up to 98.6%., Comment: 11 pages

This article describes the system submitted by the RGCL team to the IDAT 2019 Shared Task: Irony Detection in Arabic Tweets. The system detects irony in Arabic tweets using deep learning. The paper evaluates the performance of several deep learning models, as well as how text cleaning and text pre-processing influence the accuracy of the system. Several runs were submitted. The highest F1 score achieved for one of the submissions was 0.818 making the team RGCL rank 4th out of 10 teams in nal results. Overall, we present a system that uses minimal pre-processing but capable of achieving competitive results.

This work presents a hybrid heuristic search algorithm called Moth Swarm Algorithm (MSA) in the context of power loss minimization of radial distribution networks (RDN) through optimal allocation and rating of shunt capacitors for enhancing the performance of distribution networks. With MSA, different optimization operators are used to mimic a set of behavioral patterns of moths in nature, which allows for flexible and powerful optimizer. Hence, a new dynamic selection strategy of crossover points is proposed based on population diversity to handle the difference vectors Lévy-mutation to force MSA jump out of stagnation and enhance its exploration ability. In addition, a spiral motion, adaptive Gaussian walks, and a novel associative learning mechanism with immediate memory are implemented to exploit the promising areas in the search space. In this article, the MSA is tested to adapt the objective function to reduce the system power losses, reduce total system cost and consequently increase the annual net saving with inequity constrains on capacitor size and voltage limits. The validation of the proposed algorithm has been tested and verified through small, medium and large scales of standard RDN of IEEE (33, 69, 85-bus) systems and also on ring main systems of 33 and 69-bus. In addition, the obtained results are compared with other algorithms to highlight the advantages of the proposed approach. Numerical results stated that the MSA can achieve optimal solutions for losses reduction and capacitor locations with finest performance compared with many existing algorithms.

The problem of vocalization, or diacritization, is essential to many tasks in Arabic NLP. Arabic is generally written without the short vowels, which leads to one written form having several pronunciations with each pronunciation carrying its own meaning(s). In the experiments reported here, we define vocalization as a classification problem in which we decide for each character in the unvocalized word whether it is followed by a short vowel. We investigate the importance of different types of context. Our results show that the combination of using memory-based learning with only a word internal context leads to a word error rate of 6.64%. If a lexical context is added, the results deteriorate slowly.