Using Data Mining Techniques with Open Source Software to Evaluate the Various Factors Affecting Academic Performance: A Case Study of Students in the Faculty of Information Technology

Using Data Mining Techniques with Open Source Software to Evaluate the Various Factors Affecting Academic Performance: A Case Study of Students in the Faculty of Information Technology

Feras Hanandeh (Hashemite University, Faculty of Information Technology, Zarqa, Jordan), Majdi Y. Al-Shannag (Yarmouk University, Faculty of Information Technology, Irbid, Jordan) and Maha Mahdi Alkhaffaf (World Islamic Sciences University, Department of Management Information Systems, Amman, Jordan)
Copyright: © 2016 |Pages: 21
DOI: 10.4018/IJOSSP.2016040104
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


This research paper studies the different factors that could affect the Faculty of Information Technology students' accumulative averages at Jordanian Universities, by verifying the students' information, background and academic records. It also has the objective to reveal how this information will affect the students to obtain high grades in their courses. The information of the students is extracted from the students' records and its attributes are formulated as a huge database. Then, a free open source software (WEKA) which supports data mining tools and techniques are used to decide which attribute(s) will affect the students' accumulative averages. It was found that the most important factor affects the students' accumulative averages, is the student acceptance type. A decision tree model and rules are also built to determine how the students can get high grades in their courses. The overall accuracy of the model was 46.8% which is an accepted rate.
Article Preview

Literature Review

Ramaswami and Bhaskaran (2010) constructed a prediction model called CHIAD to predict the performance in higher secondary school education. They collected the input data for this model from regular students, schools and chief educational officers of different district schools, with a total of 772 student records. They found numerous factors affecting the students’ performance, like: “medium of instruction, marks obtained in secondary education, location of school, living area and type of secondary education”.

Al-Radaideh et al. (2011) provided a classification approach (data mining technique) to guide students in the basic education stage in selecting their academic tracks. They developed a decision tree classification, then they extracted a set of rules with an overall accuracy of 87.9%.

Win and Miller (2005) employed two methodologies to determine the factors that influence university students’ academic performance (analogous to an input-output approach and random coefficients’ model) by using data of first year students at the University of Western Australia in 2001. They found that high school is the most affecting factor of the academic performance of the students at the university. Further, immersion and reinforcement were affecting the performance. Their results showed that there is a strong positive relationship between the first-year mark and the Tertiary Entrance Rank (TER). It was also shown that the type of school (governmental schools or otherwise) has an effect on TER.

Chamorro-Premuzic and Furnham (2003) studied students’ neuroticism, psychotics and conscientiousness, using them as factors that affect the students’ academic performance in: exams, final-year projects, student absenteeism and essay writing. They found that neuroticism weakens academic performance, whereas conscientiousness strengthens it. Also, they found that psychotics limit academic performance. Then, they provided evidence to supporting good personality measures in academic selection procedures.

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 1 Issue (2015)
Volume 5: 3 Issues (2014)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing