SACM - United Kingdom
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9667
Browse
33 results
Search Results
Item Restricted Automatic Essay Scoring in Arabic: Development, Evaluation, and Advanced Techniques(University of Bristol, 2025) Ghazawi, Rayed; Simpson, EdwinAutomated Essay Scoring (AES) has advanced considerably due to recent progress in natural language processing (NLP). This thesis examines key challenges in AES, with a particular focus on the Arabic language, and proposes practical approaches informed by both computational techniques and educational theory. First, the research investigates how the formulation of essay questions affects the accuracy of automated scoring systems. A set of question-design criteria, derived from educational principles, is introduced and empirically tested. Experiments show that adherence to these criteria can significantly improve AES performance, with improvements of up to 40% observed using BERT-based models for English essays. Given the limited resources for Arabic AES, this thesis introduces the AR-AES dataset, consisting of 2046 essays from undergraduate students across multiple courses, annotated independently by two university instructors. This resource alleviates the scarcity of Arabic-language datasets for AES, supporting model development and evaluation. Experimental analyses using pretrained Arabic NLP models demonstrate that transformer-based approaches achieve the highest levels of agreement with human scores. In many cases, their predictions show greater consistency with the gold scores than the agreement observed between the human annotators themselves. This high level of agreement with human scores indicates that, under appropriate conditions, the proposed AES system may be suitable for assisting human markers in real-world educational settings. Additionally, the thesis explores the potential of large language models (LLMs), including ChatGPT, Llama, Aya, Jais, and ACEGPT for Arabic AES. Experiments with different training approaches, zero-shot, few-shot, and fine-tuning, demonstrate the importance of prompt engineering. A mixed-language prompting strategy, combining Arabic essays with English scoring guidelines, was found to notably enhance model performance. Nonetheless, fine-tuned AraBERT consistently yielded the strongest results, indicating that LLMs may not yet be the most effective option for Arabic AES tasks when training data is limited. Finally, an active learning framework is introduced, integrating AraBERT with uncertainty- and diversity-based sampling strategies. This human-in-the-loop approach prioritises essays that most benefit from expert review, reducing the need for extensive manual annotation while preserving high-scoring accuracy. Rather than replacing human markers, the system complements their efforts, offering a more efficient and consistent approach to large-scale essay evaluation. Overall, this thesis advances AES by introducing explicit criteria for effective essay question design, while also addressing specific challenges in Arabic AES. It contributes a comprehensively annotated dataset, presents a systematic evaluation of state-of-the-art NLP models, and effectively integrates active learning to balance automated scoring accuracy and human involvement.8 0Item Restricted Deep Learning based Cancer Classification and Segmentation in Medical Images(Saudi Digital Library, 2025) Alharbi, Afaf; Zhang, QianniCancer has significantly threatened human life and health for many years. In the clinic, medical images analysis is the golden stand for evaluating the prediction of patient prog- nosis and treatment outcome. Generally, manually labelling tumour regions in hundreds of medical images is time- consuming and expensive for pathologists, radiologists and CT scans experts. Recently, the advancements in hardware and computer vision have allowed deep-learning-based methods to become main stream to segment tumours automatically, significantly reducing the workload of healthcare professionals. However, there still remain many challenging tasks towards medical images such as auto- mated cancer categorisation, tumour area segmentation, and relying on large-scale labeled images. Therefore, this research studies theses challenges tasks in medical images proposing novel deep-learning paradigms that can support healthcare professionals in cancer diagnosis and treatment plans. Chapter 3 proposes automated tissue classification framework called Multiple Instance Learning (MIL) in whole slide histology images. To overcome the limitations of weak super- vision in tissue classification, we incorporate the attention mechanism into the MIL frame- work. This integration allows us to effectively address the challenges associated with the inadequate labeling of training data and improve the accuracy and reliability of the tissue classification process. Chapter 4 proposes a novel approach for histopathology image classification with MIL model that combines an adaptive attention mechanism into an end-to-end deep CNN as well as transfer learning pre-trained models (Trans-AMIL). Well-known Transfer Learning architectures of VGGNet [14], DenseNet [15] and ResNet[16] are leverage in our framework implementation. Experiment and deep analysis have been conducted on public histopathol- ogy breast cancer dataset. The results show that our Trans-AMIL proposed approach with VGG pre- trained model demonstrates excellent improvement over the state-of-the-art. Chapter 5 proposes a self-supervised learning for Magnetic resonance imaging (MRI) tu- mour segmentation. A self-supervised cancer segmentation framework is proposed to re- duce label dependency. An innovative Barlow-Twins technique scheme combined with swin transformer is developed to perform this self supervised method in MRI brain medical im- ages. Additionally, data augmentation are applied to improve the discriminability of tumour features. Experimental results show that the proposed method achieves better tumour seg- mentation performance than other popular self- supervised methods. Chapter 6 proposes an innovative Barlow Twins self supervised technique combined with Regularised variational auto-encoder for MRI tumour images as well as CT scans images segmentation task. A self-supervised cancer segmentation framework is proposed to reduce label dependency. An innovative Barlow-Twins technique scheme is developed to represent tumour features based on unlabeled images. Additionally, data augmentation are applied to improve the discriminability of tumour features. Experimental results show that the pro- posed method achieves better tumour segmentation performance than other existing state of the art methods. The thesis presents four approaches for classifying and segmenting cancer images from his- tology images, MRI images and CT scans images: unsupervised, and weakly supervised methods. This research effectively classifies histopathology images tumour regions based on histopathological annotations and well-designed modules. The research additionally comprehensively segments MRI and CT images. Our studies comprehensively demonstrate label-effective automatic on various types of medical image classification and segmentation. Experimental results prove that our works achieve state-of-the-art performances on both classification and segmentation tasks on real world datasets16 0Item Restricted AI Impersonation on social media Analysing Human Characteristics and Ethical Implications(Saudi Digital Library, 2025) Almuammar, Eyad; Fahad, AhmadThis study explores the behavioural, ethical, social, and regulatory implications of AI bots that impersonate humans on social media platforms. As artificial intelligence becomes increasingly integrated into online communication, AI-driven bots are being deployed to mimic human users, influence opinions, and automate engagement. While these technologies offer efficiency, they also raise serious concerns about misinformation, manipulation, transparency, and digital trust. Using a structured online questionnaire distributed via platforms such as Twitter (X), LinkedIn, and WhatsApp, this research gathered responses from 57 participants. The survey examined user perceptions across multiple dimensions, including their confidence in identifying bots, behavioural changes due to bot exposure, ethical concerns, perceived political influence, and expectations for regulation and education. Findings indicate that while many users feel moderately confident in recognizing bots, they also express reduced trust and engagement when bots are suspected. Ethical concerns particularly around privacy and undisclosed AI interaction were prominent, and users widely supported stronger regulation, transparency tools, and public education initiatives. The study concludes that AI bots pose a significant challenge to online authenticity and democratic discourse and highlights the need for multi-stakeholder governance to ensure safe and ethical deployment of such technologies.17 0Item Restricted Artificial Intelligence for Automatic Attachment Assessment in School-Age Children: An Approach Based on Language and Paralanguage.(Saudi Digital Library, 2025-06-17) Buker, Areej; Vinciarelli, AlessandroAttachment is a psychological construct that provides a framework for understanding how individuals perceive and interpret social interactions, navigate relational dynamics, and experience and regulate their emotional states, particularly under conditions of stress. An attachment style begins to develop within the first few months of life, shaped by a child’s interactions with their primary caregivers. Consistent and nurturing care promotes the development of a secure attachment style, whereas inconsistent or inadequate caregiving often gives rise to insecure attachment patterns. Insecure attachment is linked to a range of challenges, including behavioural issues such as antisocial tendencies; mental health difficulties like anxiety, emotional dysregulation, and body image concerns; and heightened risks of physical health problems, including sleep disturbances. Early recognition and intervention for insecure attachment increases the likelihood of reshaping maladaptive patterns into secure ones, potentially reducing attachment-related challenges. Automated approaches for attachment recognition offer significant benefits, including consistent delivery of assessments, such as the MCAST, and broader accessibility to a wider population. While there are a few available systems for delivering attachment tests (e.g., CMCAST and SAM), the limited studies focused on developing automated classifiers to analyse the collected data have shown a suboptimal performance. These classifiers often struggle to recognise insecure attachment, achieving a maximum Accuracy of only 62.7%. Furthermore, these studies fail to offer insights into the reasoning behind their classifications, missing an opportunity to advance the understanding of attachment in early to middle childhood. This developmental stage—characterised by significant changes that include the expansion of social circles and the internalisation of emotional representations—has historically received less attention in a field predominantly focused on studying attachment markers in infants and adults. This thesis focuses on two primary objectives: enhancing the automated classification of attachment styles in children, particularly insecure attachment, and identifying markers associated with these styles. The study employs two modalities—language and paralanguage— along with emotions derived from both modalities. These modalities are utilised within a unimodal and a multimodal framework. Among all classifiers developed using the same dataset, the language-based unimodal approach demonstrated the highest effectiveness, achieving exceptional performance in recognising insecure attachment with an Accuracy of 82.2%, all while relying on relatively simple methodologies. Furthermore, this research identified linguistic, acoustic, and emotional markers of attachment, offering valuable insights into attachment representations in children.52 0Item Restricted The ethical implications of using Multimodal Learning Analytics: a framework for research and practice(University College London (UCL), 2025) Alwahaby, Hifa; Cukurova, MutluA growing number of multimodal data (MMD) streams and complex artificial intelligence (AI) models are being used in learning analytics research to allow us to better understand, model and support learning, together with teaching processes. Considering MMDs’ potentially more invasive, extremely granular and temporal nature compared to log files, they may present additional ethical challenges in comparison to more traditional learning activity data. The systematic review undertaken during this study revealed a dearth of ethical considerations in previous multimodal learning analytics (MMLA) literature. Consequently, this study aims to identify the ethical issues associated with the use of MMLA and propose a practical framework to assist end-users to become more aware of these issues and potentially mitigate them. To gain a better understanding of the ethical issues and how they may be mitigated, the study aims to investigate the ethical concerns associated with the use of MMLA in higher education by collecting the opinions and experiences of appropriate stakeholders. Accordingly, structured individual interviews were conducted via Microsoft Teams, a video conferencing software, due to COVID-19 restrictions. In total, 60 interviews were conducted with educational stakeholders (39 higher education students, 12 researchers, eight educators and one representative of an educational technology company). Based on the thematic coding of verbatim transcriptions, nine distinct themes were identified. In response to the themes and accompanying probing questions presented to the MMLA stakeholders, and based on the ethical guidance and recommendations identified from previous literature, a first draft of the MMLA ethical framework was prepared. Subsequently, the draft was evaluated by 27 evaluators (seven higher-education students, 13 researchers–practitioners, four teachers, one ethics expert and two policymakers) by means of structured interviews. Additionally, a group of researchers adopted the framework in their research and provided constructive feedback. Based on the thematic analysis of the interviews, the framework was continually improved for three rounds until data saturation was achieved. This resulted in the presentation of the first MMLA ethical framework, which was the principal goal of this study. This thesis delivers three key contributions: (1) a systematic review of previous MMLA literature that confirms the lack of ethical considerations in the literature; (2) an examination of the ethical issues connected with MMLA from the perspective of different stakeholders; and (3) an ethical MMLA framework for higher education. By developing the framework, this thesis aims to increase awareness of the potential ethical issues and therefore, alleviate them by promoting a more ethical design, along with the development and use of MMLA in a higher education setting.24 0Item Restricted PerfectHR: Using AI to Reduce Candidate-Job Mismatch and Improve Recruitment Efficiency(Queen Mary University of London, 2025) Baraheem, Ghadeer; Wijetunge, PiyajithThe recruitment process is critical for organizations to find the right talent. However, existing recruitment software often faces issues like candidate-job mismatches and biases, leading to inefficient hiring processes. This paper presents PerfectHR, a recruitment software solution designed to reduce candidate-job mismatches and improve recruitment efficiency using artificial intelligence. The software integrates a logistic regression model for candidate classification and OpenAI’s GPT-4 language model for CV summarization. PerfectHR addresses bias in the dataset and algorithm by excluding sensitive features such as age and gender to ensure that they do not influence the model predictions. The application was developed using React.js for the frontend, Node.js for the backend, MongoDB for database management, and deployed on Vercel. Initial testing indicates that PerfectHR provides a reliable and user-friendly experience, effectively supporting job postings, candidate evaluations, and communication. Future work will focus on expanding the training dataset to cover a broader range of job types and further refining the application to improve performance and scalability.28 0Item Restricted Sharper Swords, Tougher Shields The Impact of GenAI on the Offensive-Defensive Balance in Cyberspace(King’s College London, 2024-08-26) Abanumay, Sarah; Devanny, JosephThis dissertation investigates the relative advantages of generative artificial intelligence (GenAI) to cyber defensive and offensive operations. It examines how state and non-state actors can utilise GenAI, arguing that while GenAI can significantly enhance both offensive and defensive cyber operations, the extent of these benefits is determined by four interrelated factors: geostrategic priorities, economic resources, regulatory frameworks, and organisational capabilities. These factors collectively shape the cyber offensive-defensive balance, a central concept in this study for understanding GenAI's impact on cyber operations. The research follows a literature-based methodology guided by frameworks such as the NIST Cybersecurity Framework 2.0 and the Cyber Kill Chain. The dissertation is structured into three chapters: the evolution of GenAI in cybersecurity, an analysis of strategic debates and the offensive-defensive balance and an exploration of the factors shaping this balance. The findings provide valuable insights for maintaining cybersecurity in the GenAI era.23 0Item Restricted Integrating Artificial Intelligence Technologies in Sustainable Project Management(University of Exeter, 2024-07-04) Alqurashi, Abdullah; Roman, Jose MelenezSustainable project management encompassed the economic, environmental, and social aspects of a project to attain the project objectives in a sustainable manner. Nonetheless, the integration of AI technologies in sustainable project management was still low due to factors like inadequate knowledge of technical know-how, costs of implementing AI technologies, and resistance from the project team. This research aimed to identify the factors that hinder the application of AI in project management for sustainable practices and provided recommendations for enhanced application. The research sought to understand the status of AI adoption, challenges faced, and the impact of knowledge management practices on project performance based on the survey of 40 professionals in Saudi Arabia. The findings of this research enhanced the theoretical understanding of the topic by identifying that the level of awareness of AI is much higher than the level of its adoption. The research results show that although the level of awareness of AI technologies is relatively high, the implementation of the technologies is limited because of technical, financial, and organizational constraints. This research has also highlighted how knowledge management practice can be used to close this gap which can enhance increase in project performance, reduce costs and promote innovation. The research provided practical recommendations for organizations interested in using AI for sustainability and following best practices on a global level and in alignment with the vision of Saudi Arabia for the future. When applying these recommendations, professionals will be able to increase project efficiency, reduce costs, and promote innovation which contributes to sustainable development goals. This research presents a conceptual model that outlines how AI technologies can be applied in sustainable project management, fostering innovation and sustainable development. The research also highlights the necessity for future research to delve deeper into developing actionable frameworks and practical strategies for integrating AI into sustainable project management.90 0Item Restricted IS THE METAVERSEFAILING? ANALYSINGSENTIMENTS TOWARDSTHEMETAVERSE(The University of Manchester, 2024) Alharbi, Manal Dowaihi; Batista-navarro, RizaThis dissertation investigates Aspect-Based Sentiment Analysis (ABSA) within the context of the Metaverse to better understand opinions on this emerging digital environment, particularly from a news perspective. The Metaverse, a virtual space where users can engage in various experiences, has attracted both positive and negative opinions, making it crucial to explore these sentiments to gain insights into public perspectives. A novel dataset of news articles related to the Metaverse was created, and Target Aspect-Sentiment Detection (TASD) models were applied to analyze sentiments ex pressed toward various aspects of the Metaverse, such as device performance and user privacy. A key contribution of this research is the evaluation of the TASD architecture, TAS-BERT, and its enhanced version, Advanced TAS-BERT (ATAS-BERT), which performs each task separately, on two datasets: the newly created Metaverse dataset and the SemEval15 Restaurant dataset. They were tested with different Transformer based models, including BERT, DeBERTa, RoBERTa, and ALBERT, to assess performance, particularly in cases where the target is implicit. The findings demonstrate the ability of advanced Transformer models to handle complex tasks, even when the target is implicit. ALBERT performed well on the simpler Metaverse dataset, while DeBERTa and RoBERTa showed superior performance on both datasets. This dissertation also suggests several areas for improvement in future research, such as processing paragraphs instead of individual sentences, utilizing Meta AI models for dataset annotation to enhance accuracy, and designing architectures specifically for models like DeBERTa, RoBERTa, and ALBERT, rather than relying on architectures originally designed for BERT, to improve performance. Additionally, incorporating enriched context representations, such as Part-of-Speech tags, could further enhance model performance.16 0Item Restricted Leveraging Brain-Computer Interface Technology to Interpret Intentions and Enable Cognitive Human-Computer Interaction(Univeristy of Manchester, 2024) Alsaddique, Luay; Breitling, RainerIn this paper, I present the developed, integration, and evaluation of a Brain–Computer Interface (BCI) system which showcases the accessibility and usability of a BCI head- set to interact external devices and services. The paper initially provides a detailed survey of the history of BCI technology and gives a comprehensive overview of BCI paradigms and the underpinning biology of the brain, current BCI technologies, recent advances in the field, the BCI headset market, and prospective applications of the technology. The research focuses on leveraging BCI headsets within a BCI platform to interface with these external end-points through the Motor Imagery BCI paradigm. I present the design, implementation, and evaluation of a fully functioning, efficient, and versatile BCI system which can trigger real-world commands in devices and digital services. The BCI system demonstrates its versatility through use cases such as control- ling IoT devices, infrared (IR) based devices, and interacting with advanced language models. The system’s performance was quantified across various conditions, achiev- ing detection probabilities exceeding 95%, with latency as low as 1.4 seconds when hosted on a laptop and 2.1 seconds when hosted on a Raspberry Pi. The paper concludes with a detailed analysis of the limitations and potential im- provements of the newly developed system, and its implications for possible appli- cations. It also includes a comparative evaluation of latency, power efficiency, and usability, when hosting the BCI system on a laptop versus a Raspberry Pi.44 0