Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
9 results
Search Results
Item Restricted MODELING AND REASONING WITH NON-FUNCTIONAL REQUIREMENTS USING GENERATIVE AI(Saudi Digital Library, 2026) Alshomar, Ahmad Mohammad; Chung, LawrenceNon-functional requirements (NFRs), such as usability and security, can often be subjective, and achieving one NFR can help or hurt other NFRs, as different people may view, interpret, and evaluate them differently. This challenge is compounded because NFRs are often stated briefly and vaguely in informal, natural language. However, this informal NFR description makes it difficult to detect deficiencies, reason about trade-offs, and model NFRs correctly using Softgoal Interdependency Graphs (SIGs). As a result, the practice of NFR modeling remains limited, partly due to unfamiliarity with modeling languages like SIG and insufficient understanding of relevant NFRs. Recently, Generative AI (GenAI) demonstrated some familiarity with NFRs and SIG modeling concepts, such as goal decomposition and operationalization; however, it often lacks formal syntax of SIG-specific syntax, which limits its ability to generate correct NFR models. Training GenAI on SIG modeling is also not an easy task, as there are few real-world examples of SIG models. This dissertation presents the ReGenAI framework for generating and translating Informal NFR descriptions to Semi-formal SIG Models. We propose five main technical contributions. First, a domain-independent, activity-oriented ontology and process for ReGenAI are explicitly and formally presented to describe categories of essential SIG concepts, relationships, and constraints needed to generate and transform informal NFR descriptions into semi-formal SIG models. The ontology and process ensure traceability from textual statements to SIG model elements while reducing omissions and commissions in the resulting model. Second, a Backus–Naur Form (BNF)-based formal textual grammar was developed to enforce syntactic correctness and constrain GenAI-based generation, guiding the GenAI to generate SIGs that align with formal notation. Third, the SIG-GPT method is introduced as a GenAI-based generator grounded in retrieval-augmented generation (RAG) and constrained by textual grammar, enabling the generation and translation of SIG structures that align with SIG formal notation and ensuring it is ready for seamless integration with visual modeling tools. Fourth, a set of formalized validation rules is described for semantic reasoning to identify and detect modeling gaps and inconsistencies in the generated SIG models, ensuring that the models preserve the intended meaning defined in the SIG ontology. Fifth, a repair method is presented to complete and correct the detected deficiencies by repairing the missing parts into a final validated SIG model using retrieval-augmented generation (RAG) grounded in external NFR knowledge sources. To see the strengths and weaknesses of the ReGenAI framework, two experimental studies were conducted using PURE, a dataset of public requirements documents, and FISMA, a U.S. federal information security regulation, as a realistic case studies to produce semi-formal SIG models from informal NFR descriptions and to detect modeling deficiencies in transforming the source descriptions to the target models. We believe that our proposed framework can help generate, validate, and repair modeling deficiencies that negatively affect an NFR goal, providing insights into the detected gaps and how they impact the generated SIG model.2 0Item Restricted Exploring Challenges and Design Opportunities for Digital Mental Well-Being Support in Saudi Arabia: Perspectives of Young Saudi Women(Saudi Digital Library, 2025) Aldaweesh, Sarah Abdullah; Shadbolt, Nigel; Kleek, Max VanSaudi women are experiencing growing mental well-being challenges, often concealed by social barriers and stigma that discourage help-seeking. While digital support holds promise for circumventing such obstacles, its application within Saudi Arabia remains underexplored, especially in addressing Saudi users' unique cultural and religious needs. This DPhil research investigates the use of mobile mental well-being apps in Saudi Arabia, with a focus on identifying opportunities and barriers that affect their adoption and engagement. The aim is to inform the design of digital mental well-being technologies tailored to the needs of Saudi users, with a particular focus on young Saudi women, who represent a key user group for these technologies. The research comprises four empirical investigations. First, we conducted a systematic app review and content analysis of Arabic mental well-being apps available in the Saudi iOS and Android app stores. The analysis examined app features, engagement strategies, and the types of mental well-being support provided. Second, we conducted interviews with young Saudi women to examine their perceptions and experiences with mental well-being apps and to understand how cultural, religious, and social factors affect their engagement with mental well-being apps. Third, we ran a series of co-design workshops with young Saudi women to elicit their design preferences and requirements for mental well-being apps. This resulted in five empirically and theoretically grounded design recommendations to address identified challenges and improve the future design of well-being apps in the Saudi context. In the fourth and final study, building on the findings from the earlier studies, we incorporated our proposed design recommendations into an LLM-based technology probe to examine their acceptability, with a particular focus on cultural alignment. We then evaluated this prototype through user interviews with a group from the target population to assess its relevance and acceptability. This study also contributes to emerging research on LLMs by exploring the cultural sensitivity of LLMs and examining whether empirically informed prompts can enhance cultural alignment. The findings of this thesis contribute to the fields of Human-Computer Interaction (HCI) and digital mental well-being support by informing the future design of technologies for young Saudi women, and the broader population of Muslim Arab women.15 0Item Restricted Adoption of AI Itinerary Planners by Young Adults: A UTAUT Study(Bournemouth University, 2025) Alshehri, Omar; Buhalis, DimitriosThe rapid integration of generative Artificial Intelligence (AI) into the tourism sector has created powerful new tools for travel planning. This study investigates the key determinants influencing the adoption of AI itinerary planners among young adults (aged 18-28), a critical demographic of digital natives. The research aim was to develop and empirically validate an extended Unified Theory of Acceptance and Use of Technology (UTAUT) model, integrating the core theory with the constructs of trust, personalisation, and perceived risk. A quantitative, cross-sectional online survey was administered, yielding a final sample of 228 valid responses, which were analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM). The findings reveal that Performance Expectancy is the most powerful predictor of behavioural intention, strongly affirming that perceived utility is the primary driver of adoption. Social Influence and Trust also emerged as significant positive determinants. Crucially, the model demonstrated that Perceived Personalisation is a key antecedent, strongly and positively influencing both Performance Expectancy and Trust. In contrast, Effort Expectancy and Facilitating Conditions were found to be non-significant, suggesting these are baseline expectations rather than drivers for this technologically fluent cohort. While Perceived Risk did not directly deter adoption intention, it significantly eroded user trust. The validated model demonstrated substantial explanatory power, accounting for 76.2% of the variance in behavioural intention. The study concludes that young adults' adoption of AI planners is a pragmatic decision driven by utility, social proof, and a foundation of trust cultivated through a personalised user experience. These findings recommend that industry practitioners focus on enhancing personalisation algorithms and transparency to build trust and leverage social influence in marketing efforts to encourage adoption.55 0Item Restricted The Impact of Generative AI on Teaching, Learning, and Integrity in Higher Education: A Systematic Review(Saudi Digital Library, 2025) Alghamdi, Abdullah Ali A; Kang, KyeongThis systematic review investigates the impact of Generative Artificial Intelligence (GenAI) on teaching practices, student learning, and academic integrity within higher education. This review conducted a qualitative thematic synthesis of 25 peer reviewed studies published 2020−2025, and using PRISMA 2020 framework for the review. The results will prove that GenAI will enable greater teaching efficiency, allow for more personalized learning routes, and will make education more accessible. GenAI tools are now being used by educators to automate feedback, create fresh assessments, and create differentiated instruction, while students use its AI powered platforms for academic’s support, language help, and creative exploration. The study also reveals some critical challenges. Misuse of GenAI can lead into superficial engagement and hinder the growth of critical thinking skills. The one major consideration is the development of the academic misconduct patterns, which GenAI-generated content is not being detected by traditional plagiarism detection tools. Higher education institutions may struggle to maintain academic integrity when there is robust human judgment, and redefined standards of academic authorship, in an AI enhanced environment. Responses to GenAI adoption by institutions are still uneven, going from proactive policy formulation to restrictive bans. Similar attitudes vary among disciplines, age, and tolerance for the prior digital exposure. The review highlights the necessity of universities to have clear, adaptive policy in place, incorporate AI literacy into curricula, redesign of assessments to encourage authentic learning processes, and university faculty development. To contribute to the growing dialogue on AI and education this study provides a synthesized thematic understanding of GenAI integration’s opportunities, risks, and institutional strategies. Second, it contends that GenAI must be embraced by higher education by both leveraging its benefits and mitigating its challenges for the sake of technology that offers no benefit and, even worse, threatens to undermine academic values.91 0Item Restricted The Impact of ChatGPT Use on the Motivation and Basic Psychological Needs of Saudi EFL Students(Arizona State University, 2025) Alwadai, Abdullah; Smith, BryanThe advent of generative artificial intelligence (GenAI) represents a significant technological breakthrough, enabling models like ChatGPT to facilitate human-like interactions, personalized learning, constructive feedback, and so on. The sophistication of generative AI has attracted considerable attention from researchers who explore its potential benefits for language learners. However, since it was released a few years ago, research on ChatGPT’s effectiveness in enhancing language learning motivation for English as a foreign language (EFL) learners remains limited. To this end, this research utilized the self-determination theory (SDT) to investigate the extent to which engaging in informal interactions with ChatGPT in extramural contexts influences motivation and the basic psychological needs for autonomy, competence, and relatedness. To achieve this, a quasi-experimental design was employed with fifty EFL Saudi undergraduate students majoring in English, divided equally into an experimental and a control group. The experimental group participated in nine sessions over three weeks, engaging in informal self-directed interactions with ChatGPT on common everyday topics, while the control group responded to the same topics in writing without using AI, following the same number of sessions. The post-test results analyzed using analysis of covariance (ANCOVA) indicated a substantial increase in autonomous motivation and a decrease in controlled motivation in the experimental group after the treatment. Moreover, the results revealed a significant increase in autonomy exclusively in the experimental group. However, no statistically significant difference was observed in competence and relatedness after the intervention. Informed by these findings, a number of implications and pedagogical recommendations for language instructors, policymakers, and other stakeholders were proposed.114 0Item Restricted Fake News Detection on Social Media: Methods and Techniques(University of Leeds, 2024) Althabiti, Saud; Alsalka, Mohammad Ammar; Atwell, EricThis thesis explores a number of new techniques for detecting fake news on social media and culminates with proposing a comprehensive fact-checking system. Although the main focus is on the Arabic language, the proposed methods and techniques are adaptable to other languages. The effectiveness of these methods has been evaluated through various experiments using data from social media platforms such as Twitter and other sources of potential misinformation. A literature review of studies in the field reveals a significant amount of research focused on applying AI methods to automate the detection of online fake news. However, current research in this direction has several weaknesses in various areas, including challenges in the entire detection pipeline, limitations in the employed methodologies, and inadequacies in existing datasets. The thesis begins by introducing a novel approach to simulating interactions on social networks, which enables the tracking of user behaviours and the propagation of news to assess credibility. It then examines four different techniques that can be considered for building an automatic fact-checking system and concludes with the proposal of a hybrid unified pipeline. The first technique focuses on classifying claims based solely on their content. To evaluate this approach, three studies were conducted using different methods. The proposed methods demonstrated promising results, which achieved a macro F-score of 0.339 in the third study. These findings suggest that content-based techniques can be improved by incorporating additional information. The second technique expands claim classification by incorporating both content and additional external information. New structured methodologies were developed to extract potential features rather than relying solely on claim content. Examples of such methodologies include identifying sarcastic or hateful comments. Although the results showed that these features did not improve classification performance, they highlighted the potential value of such indicators. Specifically, the findings revealed that sarcasm or hate speech is nearly twice as prevalent in comments on false claims compared to true ones. The third technique aims to automate fact-checking explainability based on the content of claims and news articles. To support this approach, a new dataset, FactEx, was collected from trusted fact-checking systems. This dataset was used to fine-tune generative models, and among these, the best-performing model achieved a ROUGE score of 23.4. The fourth technique involves fact-checking claims through retrieved information. A new verification system, named Ta’keed, was developed based on this technique to fact-check Arabic claims. Additionally, a new gold-labelled test set, ArFactEx, was compiled to assess Ta’keed. An evaluation investigation reveals that the proposed system exceeded models such as AraBERT when fine-tuned on three benchmark Arabic datasets and tested on ArFactEx. It achieved an F1-score of 0.72 compared to 0.52, 0.61, and 0.54 by the other fine-tuned models. It also outperformed T5-based and AraT5-based models in generating justifications, with an average cosine similarity score of 0.76. Finally, an optimised hybrid pipeline was introduced, which incorporates information retrieval and evidence extraction to enhance the classification task. The final proposed pipeline achieved an F1-score of 0.86, which highlighted the importance of information retrieval in tackling disinformation.80 0Item Restricted Generative AI Technologies Use Among Higher Education Students in Saudi Arabia: Benefits and Concerns(University of Southampton, 2024) AlKhunayfir, Sarah; Zarifis, AlexThis study investigates the use of generative AI technologies among higher education students in Saudi Arabia, focusing on perceived benefits and concerns. As these technologies rapidly integrate into academic environments, understanding their impact becomes crucial for effective implementation and policy development. The research aims to identify specific benefits in terms of time savings, unique insights, and personalised feedback, while also examining concerns regarding overreliance, data privacy, and information accuracy. Employing a quantitative approach, the study utilised a closed-questions survey distributed to 150 higher education students in Saudi Arabia. The survey gathered data on students' perceptions and usage patterns of generative AI technologies, which were then analysed using descriptive and inferential statistical methods. Findings reveal a nuanced landscape of student attitudes. Students perceive significant benefits from generative AI, with time savings emerging as the most appreciated advantage, followed by gaining unique insights and receiving personalised feedback. Concurrently, moderate levels of concern were identified, primarily regarding the accuracy of AI-generated content and potential overreliance on these technologies. Interestingly, data privacy concerns were less pronounced than anticipated. The study concludes that while students recognise the transformative potential of generative AI in enhancing learning experiences, they remain cautious about its limitations. These findings contribute to the understanding of AI integration in Saudi higher education and offer valuable insights for developing balanced, ethical, and effective AI integration strategies. The research underscores the need for ongoing dialogue, policy development, and further investigation to ensure that the integration of generative AI aligns with educational goals and societal values in Saudi Arabia.55 0Item Restricted Developing a Generative AI Model to Enhance Sentiment Analysis for the Saudi Dialect(Texas Tech University, 2024-12) Aftan, Sulaiman; Zhuang, YuSentiment Analysis (SA) is a fundamental task in Natural Language Processing (NLP) with broad applications across various real-world domains. While Arabic is a globally significant language with several well-developed NLP models for its standard form, achieving high performance in sentiment analysis for the Saudi Dialect (SD) remains challenging. A key factor contributing to this difficulty is inadequate SD datasets for training of NLP models. This study introduces a novel method for adapting a high-resource language model to a closely related but low-resource dialect by combining moderate effort in SD data collection with generative AI to address this problem of inadequacy in SD datasets. Then, AraBERT was fine-tuned using a combination of collected SD data and additional SD data generated by GPT. The results demonstrate a significant improvement in SD sentiment analysis performance compared to the AraBERT model, which is fine-tuned with only collected SD datasets. This approach highlights an efficient approach to generating high-quality datasets for fine-tuning a model trained on a high-resource language to perform well in a low-resource dialect. Leveraging generative AI enables reduced effort in data collection, making our approach a promising avenue for future research in low-resource NLP tasks.42 0Item Restricted Navigating Arabic Sentiments: An Evaluation of Multilingual and Arabic Dedicated Large Language Models(University of Exeter, 2024) Altowairqi, Hadeel; Menezes, RonaldoExpressing emotions in written text, especially in Arabic with its complex structure and poetic elements, can be challenging.While body language enriches spoken communication with emotional depth, written Arabic often lacks this nuance. The advent of Large Language Models (LLMs) has revolutionized natural language processing (NLP), excelling in tasks like text generation and sentiment analysis. However, the performance of these models varies significantly depending on the language and task. Arabic poses unique challenges due to its complex morphology and diverse dialects. This research investigates the impact of LLMs, particularly those tailored for Arabic, on the emotional depth of the written text. By evaluating how these models modify expressions, the study aims to understand whether LLMs preserve or constrain the intricate emotional nuances inherent in Arabic. The findings will contribute to the development of more effective AI tools for digital communication in the Arabic-speaking world, enhancing applications in fields such as sentiment analysis, opinion mining, and content moderation. Through a comprehensive analysis of over 81,000 Arabic texts, including tweets and book reviews, the study examines the performance of the general-purpose LLM ChatGPT and the Arabic-specific LLM JAIS, focusing on the sentiment shifts introduced by their edits. The results reveal a significant tendency of these models to introduce a positive bias, reducing the frequency of extremely negative sentiments. These insights highlight the necessity of incorporating cultural and linguistic nuances into LLM training data, emphasizing the importance of responsible development and ethical considerations in LLM applications.25 0