Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
3 results
Search Results
Item Restricted AUTOMATED DETECTION OF OFFENSIVE TEXTS BASED ON ENSEMBLE LEARNING AND HYBRID DEEP LEARNING TECHNIQUES(Florida Atlantic University, 2025-05) Alqahtani, Abdulkarim Faraj; Ilyas, MohammadThe impact of communication through social media is currently considered a significant social issue. This issue can lead to inappropriate behavior using social media, which is referred to as cyberbullying. The accessibility and freedom of expression afforded by social media platforms enable individuals to share their emotions and opinions, but it also leads to cyberbullying behavior. Automated systems are capable of efficiently identifying cyberbullying and performing sentiment analysis on social media platforms. In this dissertation, our focus is on enhancing a system to detect cyberbullying in various ways. Therefore, we apply natural language processing techniques utilizing artificial intelligence algorithms to identify offensive texts in various public datasets. The first approach leverages two deep learning models to classify a large-scale dataset, combining two techniques: data augmentation and the GloVe pre-trained word representation method to improve training performance. In addition, we utilized multi-classification algorithms on a cyberbullying dataset to identify six types of cyberbullying tweets. Our approach achieved high accuracy, particularly with TF-IDF (bigram) feature extraction, compared to previous experiments and traditional machine learning algorithms applied to the same dataset. We employed two ensemble machine learning methods with the TF-IDF feature extraction technique, which demonstrated superior classification performance. Moreover, we used four feature extraction methods, BoW, TF-IDF, Word2Vec, and GloVe, to determine which works best with the ensemble technique. Finally, we utilize a multi-channel convolutional neural network (CNN) enhanced with an attention mechanism and optimized using a focal loss function.10 0Item Restricted “THE APPLICATION OF AI FOR AUDIT EFFICIENCY IN THE AREA OF STOCKTAKING: THE CASE OF FIVE PUBLIC ORGANISATIONS IN KSA”(University of Essex, 2024-09) Alanazi, Homood; Oyewo, BabajideABSTRACT The integration of artificial intelligence in various types of organisations has completely revolutionized the traditional process of the organisation. Artificial intelligence has been used as an auditing tool, but KSA public sectors rely on manual or semiautomatic technologies for auditing in stocktaking. This study investigates the implementation of AI, auditing efficiency and accuracy, challenges that artificial intelligence faces, and the scope of artificial intelligence in future technology developed and recommends effective technology for the KSA public organization Saudi ARAMCO, Saudi Arabian Airlines, Saudi Basic Industries Corporation, Saudi Electricity Company, and Ministry of Health. To achieve the aim of this research, the qualitative research approach was adopted, and the data was collected through interviews with 20 top managerial positional persons. Thematic analysis was used to analyse the interview transcript in a logical sequence. This research reveals that to achieve VISION 2030; the KSA public sector is interested in implementing artificial intelligence because this can optimise the process and enhance efficiency and accuracy. This research also reveals that AI has financial, technological, and other challenges but still has the scope for future technology developments and is also an effective technology for the KSA public organisations. Keywords: Artificial intelligence (AI), auditing, stocktaking, KSA public sectors20 0Item Restricted Exploring the Experiences and Perceptions of Computed Tomography Radiologists and Radiographers Towards Introducing Artificial Intelligence Innovations in Their Practice in Saudi Arabia: A Qualitative Descriptive Study.(2023-04-03) Alsloum, Nada; Jason, ElliottBackground Artificial intelligence (AI) refers to the ability of machines to accomplish tasks that traditionally require human intelligence. In the healthcare sector, especially in the radiology field, AI has found the optimal environment to flourish and several applications have been incorporated into daily radiology workflow. This rapid integration of AI into radiology practice could have a significant impact on key radiology professionals, namely radiologists and radiographers, especially in Saudi Arabia, which aims to be the global leader in AI by 2030 under a strategic plan known as Vision 2030. Methodology A qualitative study was conducted to explore computed tomography radiographers’ and radiologists’ experiences and perceptions regarding AI adoption into radiology practice. To achieve this, eight semi-structured online interviews were conducted with six radiographers and two radiologists. The Participants were purposively sampled from three different governmental hospitals in Najran, KSA. Audio recordings of the interviews were manually transcribed and analysed by employing thematic analysis. Three themes emerged from the interviews: (1) the knowledge of radiology professionals about AI, (2) the attitudes of radiology professionals towards AI, and (3) the current AI practice in radiology. Two additional themes focused on the drivers and barriers to AI adoption in Saudi radiology practice were identified. Results The findings revealed that most radiology professionals were adequately knowledgeable about AI and its applications in radiology, although they had received no formal education or dedicated training on AI. Positivity and excitement regarding AI integration were expressed by most of the participants, and all of them were willing to use AI-based tools during their routine work. Furthermore, they generally believed in the positive impact that AI would have on radiology practice and patient care. In current radiology practice, several AI applications were used by some participants. This generally positive attitude was mainly driven by AI-appropriate awareness, Saudi Vision 2030, the perceived benefits of AI, and local champion. Despite the overall positivity, some concerns related to job insecurity, skills degradation, AI’s limited accuracy, and related medico-legal issues were raised by some participants. These concerns, in addition to the lack of AI education and training, AI-related costs, and resistance to change, were considered the main barriers to AI adoption in Saudi radiology practice. This warrants an urgent need to introduce AI-related subjects into Saudi radiology curricula, provide dedicated AI training for radiology professionals, and establish an adoption strategy and clear regulations for AI clinical use.99 0