Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted An Exploration of Word Embedding Models for Phishing Email Detection(University of Southampton, 2023-09-21) Alghamdi, Rawan; Hewitt, SarahPhishing emails are dangerous cyberattacks that attackers use to steal information. Manual solutions such as blacklists can be used to detect phishing emails. However, The emergence of machine learning solutions has made phishing email detection faster and easier. This study explored and compared the performance of three deep learning models for detecting text-based phishing emails. The models used different word embedding techniques: Word2Vec, FastText, and GloVe. All three models used a Long Short-Term Memory (LSTM) classifier. Two publicly available datasets were merged to create a balanced dataset of phishing and legitimate emails using only the body text of the emails, excluding the header. The first dataset is the Fraudulent E-mail Corpus - Nigerian Letter or ”419” Fraud, which contains phishing emails. The second dataset is the Enron Email Dataset, which contains legitimate emails. The Word2Vec- LSTM model achieved the best performance, with an F1 score of 98.62% and an accuracy of 98.62%. The FastText-LSTM also performed well, but its performance was slightly lower than the Word2Vec-LSTM model, with an F1 score of 95.73% and an accuracy of 95.73%. The GloVe-LSTM model performed poorly, with an F1 score of 55.79% and an accuracy of 60.53%. We therefore conclude that using different embedding techniques with the same classifier can result in different performances for detecting and classifying phishing and legitimate emails.46 0Item Restricted Factors impacting Saudi women’s adoption of non-traditional dress for use in public: An application of the theory of planned behavior(Saudi Digital Library, 2023) Alghamdi, Rawan; Fiore, Ann-MarieIn Saudi Arabia, women's rights are at the forefront of debate. Modernizing the country includes changes in various aspects of women’s lives, such as the relaxation of the strict public dress code. As of 2018, Saudi women are no longer required to wear traditional abayas (long black abayas with a hair covering and optional face covering) (Abdulaziz, 2019). Presently, Saudi women may choose to wear a fashionable and less conservative dress in public, as long as it is modest and adheres to Islamic guidelines. To date, it appears that research has not examined the factors that affect Saudi women's intention to purchase non-traditional abayas. The purpose of the present study was to examine the factors that impact Saudi women’s adoption of such abayas. The theory of planned behavior (TPB) was utilized. Its three key factors (attitude, subjective norms, and perceived behavioral control) are strong predictors of behavioral intention (Ajzen, 1991). To elucidate how appearance reflects an individual’s public identity, social and psychological aspects of dress theories were reviewed in the present study, including (1) the public, private, and secret self-model (Eicher, 1981), (2) self-concept theory (Sirgy, 1982), (3) symbolic consumption theory (Levy, 1959), (4) extended-self theory (Belk, 1988), and aspect of ambivalence and ambiguity. The objectives of the present study were to measure (1) the impact of the psychographic variables (the need for uniqueness and religiosity) on Saudi women’s fashion innovativeness, (2) the impact of fashion innovativeness on Saudi women’s attitude toward purchasing non- traditional public abayas, (3) the effect of attitude, subjective norms, and perceived behavioral control on Saudi women’s intentions to purchase non-traditional abayas for use in public, and (4) the moderating effect of the independent-self construal on the relationship between subjective norms and Saudi women’s intentions to purchase non-traditional abayas. A quantitative research approach (Creswell & Creswell, 2018) was implemented. A pilot study was conducted with 15 Saudi women to ensure the clarity of the survey’s wording and to determine the amount of time required. An online Arabic survey was distributed among a convenience sample of Saudi women through the social media platform (WhatsApp). A total of 1,101 Saudi women, 18 years old or older, participated in the study. The data were analyzed in three main stages, employing the following statistical tests: (1) exploratory factor analysis (EFA); (2) structural equation modeling (SEM), including confirmatory factor analysis (CFA); and (3) moderation analysis. The result of the EFA revealed that attitude and purchase intention were unexpectedly combined into one variable (attitude/purchase intention). The measurement model for the TPB variables and the combined attitude/purchase intention variable yielded an acceptable fit. Moreover, the structural model revealed the following findings: (1) the need for uniqueness had a nonsignificant impact on fashion innovativeness, (2) religiosity had a significant (but reverse) effect on fashion innovativeness, (3) fashion innovativeness had a nonsignificant impact on attitude toward purchasing non-traditional abayas, (4) subjective norms had a significant positive impact on attitude/purchase intention and perceived behavioral control, and (5) perceived behavioral control had a nonsignificant impact on attitude/purchase intention. Furthermore, the moderating effect of independent self-construal on the relationship between subjective norms and Saudi women's intentions to purchase non-traditional abayas was found to be statistically nonsignificant. The results of the fully recursive model showed the addition of six significant paths; the need for uniqueness and religiosity each had a significant direct effect on subjective norms, perceived behavioral control, and attitude/purchase intention. The absence of confirmation regarding the TPB has theoretical implications for scholars who study consumer behavior in a collectivist society. However, incorporating antecedent variables, in this case--need for uniqueness and religiosity--to the TPB model may enhance its ability to predict collectivist consumers’ behavioral intentions. The findings have the potential to benefit marketers in Saudi Arabia by enhancing their understanding of the factors that influence Saudi women’s intention to purchase non-traditional abayas. For instance, the findings suggest take religiosity level should be taken into consideration when segmenting consumers.17 0