Search results for: Arabic natural language processing

Authors: F. Abdelhamid

Abstract:

Algeria is a multilingual speech community where individuals constantly mix between codes in spoken discourse. Code is used as a cover term to refer to the existing languages and language varieties which include, among others, the mother tongue of the majority Algerian Arabic, the official language Modern Standard Arabic and the foreign languages French and English. The present study explores whether Algerians mix between these codes in online communication as well. Facebook is the selected platform from which data is collected because it is the preferred social media site for most Algerians and it is the most used one. Adopting the notion of translanguaging, this study attempts explaining how users of Facebook use multilingual messages to communicate meaning. Accordingly, multilingual interactions are not approached from a pejorative perspective but rather as a creative linguistic behavior that multilingual utilize to achieve intended meanings. The study is intended as a contribution to the research on multilingualism online because although an extensive literature has investigated multilingualism in spoken discourse, limited research investigated it in the online one. Its aim is two-fold. First, it aims at ensuring that the selected platform for analysis, namely Facebook, could be a source for multilingual data to enable the qualitative analysis. This is done by measuring frequency rates of multilingual instances. Second, when enough multilingual instances are encountered, it aims at describing and interpreting some selected ones. 120 posts and 16335 comments were collected from two Facebook pages. Analysis revealed that third of the collected data are multilingual messages. Users of Facebook mixed between the four mentioned codes in writing their messages. The most frequent cases are mixing between Algerian Arabic and French and between Algerian Arabic and Modern Standard Arabic. A focused qualitative analysis followed where some examples are interpreted and explained. It seems that Algerians mix between codes when communicating online despite the fact that it is a conscious type of communication. This suggests that such behavior is not a random and corrupted way of communicating but rather an intentional and natural one.

Keywords: Algerian speech community, computer mediated communication, languages in contact, multilingualism, translanguaging

Procedia PDF Downloads 131

Authors: Erfan Abdeldaim Mohamed Ahmed Abdalla

Abstract:

The era of the knowledge explosion in which we live requires us to develop educational curricula quantitatively and qualitatively to adapt to the twenty-first-century skills of critical thinking, problem-solving, communication, cooperation, creativity, and innovation. The process of developing the curriculum is as significant as building it; in fact, the development of curricula may be more difficult than building them. And curriculum development includes analyzing needs, setting goals, designing the content and educational materials, creating language programs, developing teachers, applying for programmes in schools, monitoring and feedback, and then evaluating the language programme resulting from these processes. When we look back at the history of language teaching during the twentieth century, we find that developing the delivery method is the most crucial aspect of change in language teaching doctrines. The concept of delivery method in teaching is a systematic set of teaching practices based on a specific theory of language acquisition. This is a key consideration, as the process of development must include all the curriculum elements in its comprehensive sense: linguistically and non-linguistically. The various Arabic curricula provide the student with a set of units, each unit consisting of a set of linguistic elements. These elements are often not logically arranged, and more importantly, they neglect essential points and highlight other less important ones. Moreover, the educational curricula entail a great deal of monotony in the presentation of content, which makes it hard for the teacher to select adequate content; so that the teacher often navigates among diverse references to prepare a lesson and hardly finds the suitable one. Similarly, the student often gets bored when learning the Arabic language and fails to fulfill considerable progress in it. Therefore, the problem is not related to the lack of curricula, but the problem is the development of the curriculum with all its linguistic and non-linguistic elements in accordance with contemporary challenges and standards for teaching foreign languages. The Arabic library suffers from a lack of references for curriculum development. In this paper, the researcher investigates the elements of development, such as the teacher, content, methods, objectives, evaluation, and activities. Hence, a set of general guidelines in the field of educational development were reached. The paper highlights the need to identify weaknesses in educational curricula, decide the twenty-first-century skills that must be employed in Arabic education curricula, and the employment of foreign language teaching standards in current Arabic Curricula. The researcher assumes that the series of teaching Arabic to speakers of other languages in regular schools do not address the skills of the twenty-first century, which is what the researcher tries to apply in the proposed unit. The experimental method is the method of this study. It is based on two groups: experimental and control. The development of an educational unit will help build suitable educational series for students of the Arabic language in regular schools, in which twenty-first-century skills and standards for teaching foreign languages will be addressed and be more useful and attractive to students.

Keywords: curriculum, development, Arabic language, non-native, skills

Procedia PDF Downloads 84

Authors: Jaspreet Singh, Gurvinder Singh, Prabhsimran Singh, Rajinder Singh, Prithvipal Singh, Karanjeet Singh Kahlon, Ravinder Singh Sawhney

Abstract:

Morphological evaluation of Indian languages is one of the burgeoning fields in the area of Natural Language Processing (NLP). The evaluation of a language is an eminent task in the era of information retrieval and text mining. The extraction and classification of knowledge from text can be exploited for sentiment analysis and morphological evaluation. This study coalesce morphological evaluation and sentiment analysis for the task of classification of farmer suicide cases reported in Punjab state of India. The pre-processing of Punjabi text involves morphological evaluation and normalization of Punjabi word tokens followed by the training of proposed model using deep learning classification on Punjabi language text extracted from online Punjabi news reports. The class-wise accuracies of sentiment prediction for four negatively oriented classes of farmer suicide cases are 93.85%, 88.53%, 83.3%, and 95.45% respectively. The overall accuracy of sentiment classification obtained using proposed framework on 275 Punjabi text documents is found to be 90.29%.

Keywords: deep neural network, farmer suicides, morphological processing, punjabi text, sentiment analysis

Procedia PDF Downloads 327

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 108

Authors: S. AlBustan, B. AlGhannam

Abstract:

This oral presentation discusses a proposal for a study that evaluates the usability of an evidence based application named ProxTalker App. The significance of this study will inform administration and faculty staff at the Department of Communication Sciences Disorders (CDS), College of Life Sciences, Kuwait University whether the app is a suitable tool to use for CDS students. A case study will be used involving a sample of CDS students taking practicum and internship courses during the academic year 2018/2019. The study will follow a process used by previous study. The process of calculating SUS is well documented and will be followed. ProxTalker App is an alternative and augmentative tool that speech language pathologist (SLP) can use to customize boards for their clients. SLPs can customize different boards using this app for various activities. A board can be created by the SLP to improve and support receptive and expressive language. Using technology to support therapy can aid SLPs to integrate this ProxTalker App as part of their clients therapy. Supported tools, games and motivation are some advantages of incorporating apps during therapy sessions. A quantitative methodology will be used. It involves the utilization of a standard tool that was the was adapted to the Arabic language to accommodate native Arabic language users. The tool that will be utilized in this research is the Arabic Standard Usability Scale (A-SUS) questionnaire which is an adoption of System Usability Scale (SUS). Standard usability questionnaires are reliable, valid and their process is properly documented. This study builds upon the development of A-SUS, which is a psychometrically evaluated questionnaire that targets Arabic native speakers. Results of the usability will give preliminary indication of whether the ProxTalker App under investigation is appropriate to be integrated within the practicum and internship curriculum of CDS. The results of this study will inform the CDS department of this specific app is an appropriate tool to be used for our specific students within our environment because usability depends on the product, environment, and users.

Keywords: A-SUS, communication disorders practicum, evidence based app, Standard Usability Scale

Procedia PDF Downloads 157

Authors: Samantha Rix

Abstract:

The purpose of this research paper is to investigate the cognitive processing of learners who receive input but produce very little or no output, and who, when they do produce output, exhibit a similar language proficiency as do those learners who produced output more regularly in the language classroom. Previous studies have investigated the benefits of output (with somewhat differing results); therefore, the presentation will begin with an investigation of what may underlie gains in proficiency without output. Consequently, a pilot study was designed and conducted to gain insight into the cognitive processing of low-output language learners looking, for example, at quantity and quality of noticing. This will be carried out within the paradigm of action classroom research, observing and interviewing low-output language learners in an intensive English program at a small Midwest university. The results of the pilot study indicated that autonomy in language learning, specifically utilizing strategies such self-monitoring, self-talk, and thinking 'out-loud', were crucial in the development of language proficiency for academic-level performance. The presentation concludes with an examination of pedagogical implication for classroom use in order to aide students in their language development.

Keywords: cognitive processing, language learners, language proficiency, learning strategies

Procedia PDF Downloads 475

Authors: C. Brierley, H. El-Farahaty, A. Farhan

Abstract:

The Leeds Parallel Corpus of Arabic-English Constitutions is a parallel corpus for the Arabic legal domain. Analysis of legal language via Corpus Linguistics techniques is an important development. In legal proceedings, a corpus-based approach to disambiguating meaning is set to replace the dictionary as an interpretative tool, and legal scholarship in the States is now attuned to the potential for Text Analytics over vast quantities of text-based legal material, following the business and medical industries. This trend is reflected in Europe: the interdisciplinary research group in Computer Assisted Legal Linguistics mines big data collections of legal and non-legal texts to analyse: legal interpretations; legal discourse; the comprehensibility of legal texts; conflict resolution; and linguistic human rights. This paper focuses on ‘dignity’ as an important aspect of the overarching concept of human rights in current constitutions across the Arab world. We have compiled a parallel, Arabic-English raw text corpus (169,861 Arabic words and 205,893 English words) from reputable websites such as the World Intellectual Property Organisation and CONSTITUTE, and uploaded and queried our corpus in Sketch Engine. Our most challenging task was sentence-level alignment of Arabic-English data. This entailed manual intervention to ensure correspondence on a one-to-many basis since Arabic sentences differ from English in length and punctuation. We have searched for morphological variants of ‘dignity’ (رامة ك, karāma) in the Arabic data and inspected their English translation equivalents. The term occurs most frequently in the Sudanese constitution (10 instances), and not at all in the constitution of Palestine. Its most frequent collocate, determined via the logDice statistic in Sketch Engine, is ‘human’ as in ‘human dignity’.

Keywords: Arabic constitution, corpus-based legal linguistics, human rights, parallel Arabic-English legal corpora

Procedia PDF Downloads 183

Authors: Sharafat Karimi, Jamil Jafari

Abstract:

The impact of Western Literature on other nations' pieces of literature (including Arabic) has caused critics to ignore the importance of Arabic cultural & literary heritage in the formation of contemporary Arabic fiction; but on the contrary, an important part of literary genres in any society, especially fiction has been formed in the past and depends on ancient literary events. The current paper, utilizing the descriptive-analytical method and by means of library studies, tries to challenge those critics who regard Western Literature as the only effective factor on the appearance of Arabic fiction. Furthermore, this research tries to find out effective Islamic-Arabic elements on the development of Arabic novel by the investigation of some fictional works. The results show that in addition to regarding Western literature as an important factor, Arab novelists have applied their heritage, culture, and ancient history, either written or orally transmitted to the current generation, in their innovations. Among great historical works containing moral stories, allegorical legends, myths, tales of heroes, and folklore, we can refer to Arabian Nights, Kalila & Dimna, romantic stories, historical puzzles, history of Islam, history of ancient Egypt, Maqama, and Quranic stories. Famous novels like 'Hadith Isa ibn-Hisham', 'Layali Alif Layla', 'Abas al-Aqdar', 'Radoubis', 'Ahlam Shahrzad, and 'Alam Bela Kharaet' were compiled on the basis of ancient literary heritage not only in the theme but also in the structure; so one can conclude that the ancient literary-cultural heritage and Islamic-Arabian history have been influential on Arabic novel appearance and development.

Keywords: Arabic fictional literature, culture, heritage, history, language, novel

Procedia PDF Downloads 127

Authors: Tarek Soliman Mostafa Soliman Al-Nana'i

Abstract:

There are non-steady voiced augments in the Semitic languages, and in the morphological and structural augmentation, two sounds were augments in all Semitic languages at the level of the spoken language and two letters at the level of the written language, which are the hamza and the ta’. This research studies only the second of them; Therefore, we defined it as “The Voiceless Dental- alveolar common augment” (VDACA) to distinguish it from the glottal sound “Hamza”, first, middle, or last, in a noun or in a verb, in Arabic and its equivalent in the Semitic languages. What is meant by “VDACA” is the ta’ that is in addition to the root of the word at the morphological level: the word “voiceless” takes out the voiced sounds that we studied before, and the “dental- alveolar common augment” takes out the laryngeal sound of them, which is the “Hamza”: and the word “common” brings out the uncommon voiceless sounds, which are sīn, shīn, and hā’. The study is limited to the ta' alone among the Arabic sounds, and this title faced a problem in identifying it with the ta'. Because the designation of the ta is not the same in most Semitic languages. Hebrew, for example, has “tav” and is pronounced with the voiced fa (v), which is not in Arabic. It is called different names in other Semitic languages, such as “taw” or “tAu” in old Syriac. And so on. This goes hand in hand with the insistence on distance from the written level and the reference to the phonetic aspect in this study that is closely and closely linked to the morphological level. Therefore, the study is “morphophonemic”. What is meant by Semitic languages in this study are the following: Akkadian, Ugaritic, Hebrew, Syriac, Mandaean, Ge'ez, and Amharic. The problem of the study is the agreement or difference between these languages in the position of that augment, first, middle, or last. And in determining the distinguishing characteristics of each language from the other. As for the study methodology, it is determined by the comparative approach in Semitic languages, which is based on the descriptive approach for each language. The study is divided into an introduction, four sections, and a conclusion: Introduction: It included the subject of the study, its importance, motives, problem, methodology, and division. The first section: VDACA as a non-common phoneme. The second: VDACA as a common phoneme. The third: VDACA as a functional morpheme. The fourth section: Commentary and conclusion with the most important results. The positions of VDACA in Arabic and other Semitic languages, and in nouns and verbs, were limited to first, middle, and last. The research identified the individual addition, which is common with other augments, and the research proved that this augmentation is constant in all Semitic languages, but there are characteristics that distinguish each language from the other.

Keywords: voiceless -, dental- alveolar, augment, Arabic - semitic languages

Procedia PDF Downloads 73

Authors: Cinthya Olivares Garita

Abstract:

Untangling language processing in second language development has been either a taken-for-granted and overlooked task for some English language teaching (ELT) instructors or a considerable feat for others. From the most traditional language instruction to the most communicative methodologies, how to assist L2 learners in processing language in the classroom has become a challenging matter in second language teaching. Amidst an ample array of methods, strategies, and techniques to teach a target language, finding a suitable model to lead learners to process, interpret, and negotiate meaning to communicate in a second language has imposed a great responsibility on language teachers; committed teachers are those who are aware of their role in equipping learners with the appropriate tools to communicate in the target language in a 21stcentury society. Unfortunately, one might find some English language teachers convinced that their job is only to lecture students; others are advocates of textbook-based instruction that might hinder second language processing, and just a few might courageously struggle to facilitate second language learning effectively. Grounded on the most representative empirical studies on comprehensible input, processing instruction, and focus on form, this analysis aims to facilitate the understanding of how second language learners process and automatize input and propose a pedagogical framework for the successful development of a second language. In light of this, this paper is structured to tackle noticing and attention and structured input as the heart of processing instruction, comprehensible input as the missing link in second language learning, and form-meaning connections as opposed to traditional grammar approaches to language teaching. The author finishes by suggesting a pedagogical framework involving noticing-attention-comprehensible-input-form (NACIF based on their acronym) to support ELT instructors, teachers, and scholars on the challenging task of facilitating the understanding of effective second language development.

Keywords: second language development, pedagogical framework, noticing, attention, comprehensible input, form

Procedia PDF Downloads 31

Authors: Alejandro Molina-Villegas, Silvia Fernández-Sabido, Eduardo Mendoza-Vargas, Fátima Miranda-Pestaña

Abstract:

The automatic detection of indigenous languages ​​in digital texts is essential to promote their inclusion in digital media. Underrepresented languages, such as Maya, are often excluded from language detection tools like Google’s language-detection library, LANGDETECT. This study addresses these limitations by developing a hybrid language detection solution that accurately distinguishes Maya (YUA) from Spanish (ES). Two strategies are employed: the first focuses on creating a profile for the Maya language within the LANGDETECT library, while the second involves training a Naive Bayes classification model with two categories, YUA and ES. The process includes comprehensive data preprocessing steps, such as cleaning, normalization, tokenization, and n-gram counting, applied to text samples collected from various sources, including articles from La Jornada Maya, a major newspaper in Mexico and the only media outlet that includes a Maya section. After the training phase, a portion of the data is used to create the YUA profile within LANGDETECT, which achieves an accuracy rate above 95% in identifying the Maya language during testing. Additionally, the Naive Bayes classifier, trained and tested on the same database, achieves an accuracy close to 98% in distinguishing between Maya and Spanish, with further validation through F1 score, recall, and logarithmic scoring, without signs of overfitting. This strategy, which combines the LANGDETECT profile with a Naive Bayes model, highlights an adaptable framework that can be extended to other underrepresented languages in future research. This fills a gap in Natural Language Processing and supports the preservation and revitalization of these languages.

Keywords: indigenous languages, language detection, Maya language, Naive Bayes classifier, natural language processing, low-resource languages

Procedia PDF Downloads 18

Authors: Mouheb Mehdoui, Amel Fraisse, Mounir Zrigui

Abstract:

This paper explores the potential of short texts through semantic enrichment and disambiguation techniques. By employing context fusion, we aim to enhance the comprehension and utility of concise textual information. The methodologies utilized are grounded in recent advancements in natural language processing, which allow for a deeper understanding of semantics within limited text formats. Specifically, topic classification is employed to understand the context of the sentence and assess the relevance of added expressions. Additionally, word sense disambiguation is used to clarify unclear words, replacing them with more precise terms. The implications of this research extend to various applications, including information retrieval and knowledge representation. Ultimately, this work highlights the importance of refining short text processing techniques to unlock their full potential in real-world applications.

Keywords: information traffic, text summarization, word-sense disambiguation, semantic enrichment, ambiguity resolution, short text enhancement, information retrieval, contextual understanding, natural language processing, ambiguity

Procedia PDF Downloads 10

Authors: Jihan Mahmoud

Abstract:

This paper examines the role played by Arabic novelists in revolutionary change in the Arab world, discussing themes of identity, sexuality and fundamentalism as portrayed in a selection of modern and contemporary Arabic novels that are either written in English or translated from Arabic into English. It particularly focuses on the post-Naguib Mahfouz era. Taking my cue from the current political changes in the Arab world, starting with 9/11/ terrorist attacks in the USA and the UK, the ‘Arab Spring’ revolutions, the rise of political Islam and the emergence of Isis, the Islamic state in Iraq and the Levant, the study analyses the differences in the ways contemporary Arab novelists from different Arabic countries represent the interaction between identity, sexual politics and fundamentalist ideas in the Arab world, with a specific focus on the overlap between literature, religion and international politics in the region. It argues that the post-Mahfouz era marked a new phase in the development of the political Arabic novel not only as a force of resistance against political-religious oppression, but as a call for revolution as well. Thus, the Arabic novel reshapes values and prompts future action.

Keywords: Arabic novel, Islam, politics, sexuality

Procedia PDF Downloads 526

Authors: Elyes Zarrouk, Yassine Benayed, Faiez Gargouri

Abstract:

This paper presents a new hybrid model for isolated Arabic words recognition. To do this, we apply Support Vectors Machine (SVM) as an estimator of posterior probabilities within the Dynamic Bayesian networks (DBN). This paper deals a comparative study between DBN and SVM/DBN systems for multi-dialect isolated Arabic words. Performance using SVM/DBN is found to exceed that of DBNs trained on an identical task, giving higher recognition accuracy for four different Arabic dialects. In fact, the average of recognition rates for the four dialects with SVM/DBN was 87.67% while 83.01% with DBN.

Keywords: dynamic Bayesian networks, hybrid models, supports vectors machine, Arabic isolated words

Procedia PDF Downloads 560

Authors: Erfan Abdeldaim Mohamed Ahmed Abdalla

Abstract:

The complexity of Arabic grammar poses challenges for learners, particularly in relation to its arrangement, classification, abundance, and bifurcation. The challenge at hand is a result of the contextual factors that gave rise to the grammatical rules in question, as well as the pedagogical approach employed at the time, which was tailored to the needs of learners during that particular historical period. Consequently, modern-day students encounter this same obstacle. This requires a thorough examination of the arrangement and categorization of Arabic grammatical rules based on particular criteria, as well as an assessment of their objectives. Additionally, it is necessary to identify the prevalent and renowned grammatical rules, as well as those that are infrequently encountered, obscure and disregarded. This paper presents a compilation of grammatical rules that require arrangement and categorization in accordance with the standards outlined in the Common European Framework of Reference for Languages (CEFR). In addition to facilitating comprehension of the curriculum, accommodating learners' requirements, and establishing the fundamental competencies for achieving proficiency in Arabic, it is imperative to ascertain the conventions that language learners necessitate in alignment with explicitly delineated benchmarks such as the CEFR criteria. The aim of this study is to reduce the quantity of grammatical rules that are typically presented to non-native Arabic speakers in Arabic textbooks. This reduction is expected to enhance the motivation of learners to continue their Arabic language acquisition and to approach the level of proficiency of native speakers. The primary obstacle faced by learners is the intricate nature of Arabic grammar, which poses a significant challenge in the realm of study. The proliferation and complexity of regulations evident in Arabic language textbooks designed for individuals who are not native speakers is noteworthy. The inadequate organisation and delivery of the material create the impression that the grammar is being imparted to a student with the intention of memorising "Alfiyyat-Ibn-Malik." Consequently, the sequence of grammatical rules instruction was altered, with rules originally intended for later instruction being presented first and those intended for earlier instruction being presented subsequently. Students often focus on learning grammatical rules that are not necessarily required while neglecting the rules that are commonly used in everyday speech and writing. Non-Arab students are taught Arabic grammar chapters that are infrequently utilised in Arabic literature and may be a topic of debate among grammarians. The aforementioned findings are derived from the statistical analysis and investigations conducted by the researcher, which will be disclosed in due course of the research. To instruct non-Arabic speakers on grammatical rules, it is imperative to discern the most prevalent grammatical frameworks in grammar manuals and linguistic literature (study sample). The present proposal suggests the allocation of grammatical structures across linguistic levels, taking into account the guidelines of the CEFR, as well as the grammatical structures that are necessary for non-Arabic-speaking learners to generate a modern, cohesive, and comprehensible language.

Keywords: grammar, Arabic, functional, framework, problems, standards, statistical, popularity, analysis

Procedia PDF Downloads 94

Authors: H. van Rensburg, B. Adcock, B. Al Mansouri

Abstract:

This paper discusses the impact of pedagogical and learning differences on Arabic international students’ (AIS) learning when they come to study in Australia. It describes the difference in teaching and learning methods between the students’ home countries in the Arabic world and Australia. There are many research papers that discuss the general experiences of international students in the western learning systems, including Australia. However, there is little research conducted specifically about AIS learning in Australia. Therefore, the data was collected through in-depth, semi-structured interviews with AIS who are learning at an Australian regional university in Queensland. For that reason, this paper contributes to fill a gap by reporting on the learning experiences of AIS in Australia and, more specifically, on the AIS’ pedagogical experiences. Not only discussing the learning experiences of AIS, but also discussing the cultural adaptation using the Oberg’s cultural adaptation model. This paper suggests some learning strategies that may benefit AIS and academic lecturers when teaching students from a completely different culture and language.

Keywords: arabic international students, cultural adaption, learning differences, learning systems

Procedia PDF Downloads 604

Authors: Chien-Hung Chen, Yan-Chun Hsing, Yung-Chun Chang

Abstract:

The Internet has grown into a powerful medium for information dispersion and social interaction that leads to a rapid growth of social media which allows users to easily post their emotions and perspectives regarding certain topics online. Our research aims at using natural language processing and text mining techniques to explore the public emotions expressed on Twitter by analyzing the sentiment behind tweets. In this paper, we propose a composite kernel method that integrates tree kernel with the linear kernel to simultaneously exploit both the tree representation and the distributed emotion keyword representation to analyze the syntactic and content information in tweets. The experiment results demonstrate that our method can effectively detect public emotion of tweets while outperforming the other compared methods.

Keywords: emotion recognition, natural language processing, composite kernel, sentiment analysis, text mining

Procedia PDF Downloads 218

Authors: Hana Almakky, Reza Sahandi, Jacqui Taylor

Abstract:

Social media continue to grow, and user interfaces may become more appealing if cultural characteristics are incorporated into their design. Facebook was designed in the west, and the original language was English. Subsequently, the words in the user interface were translated to other languages, including Arabic. Arabic words are written from right to left, and English is written from left to right. The translated version may misrepresent the original design and users preferences may influence their culture, which should be considered in the user interface design. Previous research indicates that users are more comfortable when interacting with a user interface, which relates to their own culture. Therefore, this paper, using a survey investigates the preferences of Saudi Arabian on the Arabic version of user interface of Facebook.

Keywords: culture, social media, user interface design, Facebook, Saudi Arabia

Procedia PDF Downloads 398

Authors: Rubén Valcarce-Álvarez, Francisco Jáñez-Martino, Rocío Alaiz-Rodríguez

Abstract:

Cybersecurity challenges, including scams, drug sales, the distribution of child sexual abuse material, fake news, and hate speech on both the surface and deep web, have significantly increased over the past decade. Users who post such content often employ strategies to evade detection by automated filters. Among these tactics, text obfuscation plays an essential role in deceiving detection systems. This approach involves modifying words to make them more difficult for automated systems to interpret while remaining sufficiently readable for human users. In this work, we aim at spotting obfuscated words and the employed techniques, such as leetspeak, word inversion, punctuation changes, and mixed techniques. We benchmark Named Entity Recognition (NER) using models from the BERT family as well as two large language models (LLMs), Llama and Mistral, on XX_NER_WordCamouflage dataset. Our experiments evaluate these models by comparing their precision, recall, F1 scores, and accuracy, both overall and for each individual class.

Keywords: natural language processing (NLP), text obfuscation, named entity recognition (NER), deep learning

Procedia PDF Downloads 5

Authors: Syed Mahbubuz Zaman, A. B. M. Abrar Haque, Mehedi Hassan Nayeem, Misbah Uddin Sagor

Abstract:

Everyday e-mails are being used by millions of people as an effective form of communication over the Internet. Although e-mails allow high-speed communication, there is a constant threat known as spam. Spam e-mail is often called junk e-mails which are unsolicited and sent in bulk. These unsolicited emails cause security concerns among internet users because they are being exposed to inappropriate content. There is no guaranteed way to stop spammers who use static filters as they are bypassed very easily. In this paper, a smart system is proposed that will be using neural networks to approach spam in a different way, and meanwhile, this will also detect the most relevant features that will help to design the spam filter. Also, a comparison of different parameters for different neural network models has been shown to determine which model works best within suitable parameters.

Keywords: long short-term memory, bidirectional long short-term memory, gated recurrent unit, natural language processing, natural language processing

Procedia PDF Downloads 205

Authors: Lu Song Ma Li Zhi

Abstract:

With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.

Keywords: large language models, prompt design, data analysis, code generation

Procedia PDF Downloads 43

Authors: Belkhadir Radouane

Abstract:

In this study, author tried to explore the beliefs of some Moroccan teachers working in the delegations of Safi and Youcefia about the usefulness of first and second languages in learning the third language. More specifically, author attempted to see the extent to which these teachers believe that a first and second language can serve students in learning a third one. The first language in this context is Arabic, the second is French, and the third is English. The teachers’ beliefs were gathered through a questionnaire that was addressed via Google Forms. Then, the results were analyzed using the same application. It was found that teachers are positive about the usefulness of the first and second language in learning the third one, but most of them rarely use in a conscious way activities that serve this purpose.

Keywords: Bilinguilism, teachers beliefs, English as ESL, Morocco

Procedia PDF Downloads 56

Authors: Imen Elleuch, Wael Ouarda, Gargouri Bilel

Abstract:

We proposes in this paper a Deep Learning based approach to classify text in order to enrich an Arabic ontology based on the objects classes of Gaston Gross. Those object classes are defined by taking into account the syntactic and semantic features of the treated language. Thus, our proposed approach is a hybrid one. In fact, it is based on the one hand on the object classes that represents a knowledge based-approach on classification of text and in the other hand it uses the deep learning approach that use the word embedding-based-approach to classify text. We have applied our proposed approach on a corpus constructed from an Arabic dictionary. The obtained semantic classification of text will enrich the Arabic objects classes ontology. In fact, new classes can be added to the ontology or an expansion of the features that characterizes each object class can be updated. The obtained results are compared to a similar work that treats the same object with a classical linguistic approach for the semantic classification of text. This comparison highlight our hybrid proposed approach that can be ameliorated by broaden the dataset used in the deep learning process.

Keywords: deep-learning approach, object-classes, semantic classification, Arabic

Procedia PDF Downloads 88

Authors: Ahmed Elgadri

Abstract:

In the last thirty years, studies on cross-cultural pragmatics in general and apology strategies in specific have focused on western and East-Asian societies. A small volume of research has been conducted in investigating speech acts production by Arabic dialect speakers. Therefore, this study investigated the apology strategies used by Libyan Arabic speakers using an online Discourse Completion Task (DCT) questionnaire. The DCT consisted of six situations covering different social contexts. The survey was written in Libyan Arabic dialect to help generate vernacular speech as much as possible. The participants were 25 Libyan nationals, 12 females, and 13 males. Also, to get a deeper understanding of the motivation behind the use of certain strategies, the researcher interviewed four participants using the Libyan Arabic dialect as well. The results revealed a high use of IFID, offer of repair, and explanation. Although this might support the universality claim of speech acts strategies, it was clear that cultural norms and religion determined the choice of apology strategies significantly. This led to the discovery of new culture-specific strategies, as outlined later in this paper. This study gives an insight into politeness strategies in Libyan society, and it is hoped to contribute to the field of cross-cultural pragmatics.

Keywords: apologies, cross-cultural pragmatics, language and culture, Libyan Arabic, politeness, pragmatics, socio-pragmatics, speech acts

Procedia PDF Downloads 150

Authors: Gemma García López

Abstract:

The goal of this study is to analyze if search queries carried out in search engines such as Google, can offer emotional information about the user that performs them. Knowing the emotional state in which the Internet user is located can be a key to achieve the maximum personalization of content and the detection of worrying behaviors. For this, two studies were carried out using tools with advanced natural language processing techniques. The first study determines if a query can be classified as positive, negative or neutral, while the second study extracts emotional content from words and applies the categorical and dimensional models for the representation of emotions. In addition, we use search queries in Spanish and English to establish similarities and differences between two languages. The results revealed that text search queries performed by users on the Internet can be classified emotionally. This allows us to better understand the emotional state of the user at the time of the search, which could involve adapting the technology and personalizing the responses to different emotional states.

Keywords: emotion classification, text search queries, emotional analysis, sentiment analysis in text, natural language processing

Procedia PDF Downloads 141

Authors: Abeer Heider

Abstract:

This paper explores and classifies the different kinds of avoidances that students commonly make in the acquisition of Arabic as a second/foreign language, and suggests specific strategies to help students lessen their avoidance trends in hopes of streamlining the learning process. Students most commonly use avoidance strategies in grammar, and word choice. These different types of strategies have different implications and naturally require different approaches. Thus the question remains as to the most effective way to help students improve their Arabic, and how teachers can efficiently utilize these techniques. It is hoped that this research will contribute to understand the role of avoidance in the field of the second language acquisition in general, and as a type of input. Yet some researchers also note that similarity between L1 and L2 may be problematic as well since the learner may doubt that such similarity indeed exists and consequently avoid the identical constructions or elements (Jordens, 1977; Kellermann, 1977, 1978, 1986). In an effort to resolve this issue, a case study is being conducted. The present case study attempts to provide a broader analysis of what is acquired than is usually the case, analyzing the learners ‘accomplishments in terms of three –part framework of the components of communicative competence suggested by Michele Canale: grammatical competence, sociolinguistic competence and discourse competence. The subjects of this study are 15 students’ 22th year who came to study Arabic at Qatar University of Cairo. The 15 students are in the advanced level. They were complete intermediate level in Arabic when they arrive in Qatar for the first time. The study used discourse analytic method to examine how the first language affects students’ production and output in the second language, and how and when students use avoidance methods in their learning. The study will be conducted through Fall 2015 through analyzing audio recordings that are recorded throughout the entire semester. The recordings will be around 30 clips. The students are using supplementary listening and speaking materials. The group will be tested at the end of the term to assess any measurable difference between the techniques. Questionnaires will be administered to teachers and students before and after the semester to assess any change in attitude toward avoidance and selectivity methods. Responses to these questionnaires are analyzed and discussed to assess the relative merits of the aforementioned strategies to avoidance and selectivity to further support on. Implications and recommendations for teacher training are proposed.

Keywords: the second language acquisition, learning languages, selectivity, avoidance

Procedia PDF Downloads 277

Authors: Abdulfatah A Raji

Abstract:

This paper started with the definitions of literature, Arabic literature, transformation and went further to highlight the components of educational transformation. The general history of Arabic literature was discussed with focus on how it undergoes some transformations from pre-Islamic period through Quranic era, Abbasid literature to renaissance period in which the modernization of Arabic literature started in Egypt. It also traces the spread of Arabic literature in Nigeria from the pre-colonial era during the Kanuri rulers to Jihad of Usman Dan Fodio and the development of literature which manifested to the Teacher’s Colleges and Bayero University in Northern Nigeria. Also, the establishment of primary and post-primary schools by Muslim organizations in many cities and towns of the Western part of Nigeria. Literary criticism was also discussed in line with Arabic literature. Poetry work of eminent poets were cited to show its importance in line with educational transformation in Nigerian literature and lessons from the cited Arabic poetry works were also highlighted to include: motivation to behave well and to tolerate others, better spirits of interaction, love and co-existence among different sexes, religion etc. All these can help in developing a better educational transformation in Nigeria which can in turn help in how to conduct researches for national development. The paper recommended compulsory Arabic literature at all levels of the nations’ educational system as well as publication of Arabic books and journals to encourage peace in this era of conflicts and further transform Nigeria’s educational system for better.

Keywords: Arabic, literature, peace, development, Nigeria

Procedia PDF Downloads 476

Authors: Samhani Ismail, Tahamina Begum, Faruque Reza, Zamzuri Idris, Hafizan Juahir, Jafri Malin Abdullah

Abstract:

Holy Quran, a rhymed prosed scripture has a complete literary structure that exemplifies the peak of literary beauty. Memorizing of its verses could enhance one’s memory capacity and cognition while those who are listening to its recitation it is also believed that the Holy Quran alter brainwave producing neuronal excitation engaging with cognitive processes. 28 normal healthy subjects (male =14 & female = 14) were recruited and EEG recording was done using 128-electrode sensor net (Electrical Geosics, Inc.) with the impedance of ≤ 50kΩ. They listened to Sura Fatiha recited by Sheikh Qari Abdul Basit bin Abdus Samad. Arabic news and no sound were chosen as positive and negative control, respectively. The waveform was analysed by Fast Fourier Transform (FFT) to get the power in frequency bands. Bilateral frontal (F7, F8) and temporal region (T7, T8) showed decreased power significantly in alpha wave band in respondent stimulated by Sura Fatihah recitation reflects acoustic attention processing. However, decreased in alpha power in selective attention to memorized, and in familial but not memorized language, reveals the memorial processing in long-term memory. As a conclusion, Quranic recitation relates both cognitive element of memory and language in its listeners and memorizers.

Keywords: auditory stimulation, cognition, EEG, linguistic, memory, Quranic recitation

Procedia PDF Downloads 341

Authors: Mai Alharthy, Agnes Shiel, Hynes Sinead

Abstract:

Objectives: The objectives of the study are to translate and culturally adapt the RBMT-3 to be appropriate for use within an Arabic-speaking population and to achieve maximum equivalency between the translated and original versions and to evaluate the psychometric properties of the Arabic version of the RBMT-3. Participants' numbers are 16 (10 females and 6 males). All participants are bilingual speakers of Arabic and English, above 18 years old and with no current nor past memory impairment. Methods: The study was conducted in two stages: Translation and cultural adaptation stage: Forward and backward translations were completed by professional translators. Five out of the 14 RBMT-3 subtests required cultural adaptations. Half of the faces in the face recognition subtests were replaced with Arabic faces by a professional photographer. Pictures that are irrelevant to the Arabic culture in the picture recognition subtests were replaced. Names, story and orientations subtests were also adapted to suit the Arabic culture. An expert committee was formed to compare the translated and original versions and to advise on further changes required for test materials. Validation of the Arabic RBMT-3- pilot: 16 Participants were tested on version 1 of the English version and the two versions of the Arabic RBMT-3 ( counterbalanced ). The assessment period was 6 weeks long, with two weeks gap between tests. All assessments took place in a quiet room in the National University of Ireland Galway. Two qualified occupational therapists completed the assessments. Results: Wilcox signed-rank test was used to compare between subtest scores. Significant differences were found in the story, orientation and names subtests between the English and Arabic versions. No significant differences were found in subtests from both Arabic versions except for the story subtest. Conclusion: The story and orientation subtests should be revised by the expert committee members to make further adaptations. The rest of the Arabic RBMT-3 subtests are equivalent to the subtests of the English version. The psychometric properties of the Arabic RBMT-3 will be investigated in a larger Arabic-speaking sample in Saudi Arabia. The outcome of this research is to provide clinicians and researchers with a reliable tool to assess memory problems in Arabic speaking population.

Keywords: memory impairment, neuropsychological assessment, cultural adaptation, cognitive assessment

Procedia PDF Downloads 256

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 46