Dissertations (IT & Engineering)

Permanent URI for this community

https://bspace.buid.ac.ae/handle/1234/487

Browse

Browsing Dissertations (IT & Engineering) by Subject "academic institutions"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Factors Affecting the Intention to use E-Learning Systems in Middle East
    (The British University in Dubai (BUiD), 2014-03) Bettayeb, Anissa
    This thesis investigates the factors that influence continuance intentions to use Learning Management Systems (LMS) by faculty members as a supplement to the traditional face-to-face way of education. A theoretical model is developed by extending the Expectation Confirmation Model (ECM) with the following factors: technical support, training, computer self-efficacy and Blackboard user-interface design. Data was collected from 108 faculty members at a university in United Arab Emirates (UAE) through a qualitative approach in order to investigate the faculty members’ experiences with the LMS. The thesis found that system design and technical support factors are very important factors that affect the intention to use the system in addition to the satisfaction and usefulness .Those findings supported the assumed hypotheses in the new model and can be adapted to other similar environments to improve the continuance intentions to use LMS in academic institutions.
  • Thumbnail Image
    Item
    Predict Student Success and Performance factors by analyzing educational data using data mining techniques
    (The British University in Dubai (BUiD), 2022-03) ATIF, MUHAMMAD
    Academic institutions around the globe strive to become highly reputable and make continuous efforts to improve their students' ability to gain and apply knowledge concepts in the field. The primary outcome of the academic institutions is their student's quality of education. The academic institutions are known for their outcome product that are their students work in the practical field. The educational institutions desire to have beneficial insights to ensure the success of students and to enable them to acquire knowledge and improve their abilities. This enables the institutions to retain students, graduate students on time, make students’ workplace ready and improve the institution’s reputation. The primary aim of the study is to identify key attributes that contribute to the performance of the student. Past research has mainly focused on data related to student academic assessments grades, GPA, and student demographics. The research study includes more aspects like the number of students in class, attendance of the student in class, and due to the fact that the United Arab Emirates is a diversified multicultural country, English Language Proficiency, nationality and age of students and the instructor contributes towards student performance. The research study is performed as experimental analysis and develop models from nine machine learning algorithms including KNN, Naïve Bayes, SVM, Logistic regression, Decision Tree, Random forest, Adaboost, Bagging Classifier, and voting Classifier. The model is then applied to data collected from a reputable university that included 126,698 records with twenty-six (26) initial data attributes. The results show that the Random forest model performed better in terms of accuracy of 90.12% as compared to other models. The attendance in class attribute showed positive correlation while the number of students in class attribute showed negative correlation with the grades. The Future enhancement of the research study is to include more attributes from various aspects and also to further the study to provide recommendations for the students, instructor, and the educational institution.
  • Thumbnail Image
    Item
    Predicting Dropouts among a Homogeneous Population using a Data Mining Approach
    (The British University in Dubai (BUiD), 2019-03) BILQUISE, GHAZALA
    Student retention is one the biggest challenges facing academic institutions worldwide. Failure to retain students not only affects the student in a negative way but also hinders institutional quality and reputation. While there are several theoretical perspectives of retention, which study the factors that cause students to drop out, more recent studies rely on a data mining and machine learning approach to explore the problem of retention. In this research, we present a novel data mining approach to predict retention among a homogeneous group of students, with similar social and cultural background, at an academic institution based in the UAE. Our model successfully identifes dropouts at an early stage. It provides an early warning system that enables the institution to promptly intervene with assertive measures. Moreover, our model also effectively determines the top predictive variables of retention. Several researchers study retention by focusing on student persistence from one term to another while our study builds a predictive model to study retention until graduation. Moreover, other works use additional student data for predictions, thereby reducing the dataset size, which is counter productive to data mining. Our research relies solely on pre-college and college performance data available in the institutional database. Our research reveals that the Gradient Boosted Trees is a robust algorithm that predicts dropouts with an accuracy of 79.31% and AUC of 88.4% using only pre-enrollment data. High School Average and High School stream of study are observed to be the top predictive variables of on-time graduation when a student joins college. Our study also reveals that ensemble machine learning algorithms are more reliable and outperform standard algorithms.