Tracking student performance in introductory programming by means of machine learning

Ijaz Khan, Abir Al Sadiri, Abd Rahim Ahmad, Nafaa Jabeur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

large amount of digital data is being generated across a wide variety of fields and Data Mining (DM) techniques are used transform it into useful information so as to identify hidden patterns. One of the key areas of the application of Education Data Mining (EDM) is the development of student performance prediction models that would predict the student's performance in educational institutions. We build a model which can notify students (in introductory programming course) about their probable outcomes at an early stage of the semester (when evaluated for 15% grades). We applied 11 Machine Learning algorithms (from 5 categories) over a data source using WEKA and concluded that Decision Tree (J48) is giving higher accuracy in terms of correctly identified instances, F-Measure rate and true positive detections. This study will help to the students to identify their probable final grades and modify their academic behavior accordingly to achieve higher grades.

Original languageEnglish
Title of host publication2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538680469
DOIs
Publication statusPublished - 19 Feb 2019
Event4th MEC International Conference on Big Data and Smart City, ICBDSC 2019 - Muscat, Oman
Duration: 15 Jan 201916 Jan 2019

Publication series

Name2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019

Conference

Conference4th MEC International Conference on Big Data and Smart City, ICBDSC 2019
CountryOman
CityMuscat
Period15/01/1916/01/19

Fingerprint

Computer programming
Learning systems
student
programming
Students
data mining
learning
performance
Data mining
Decision trees
educational institution
Learning algorithms
semester
transform
Education
education
machine learning
prediction

All Science Journal Classification (ASJC) codes

  • Development
  • Computer Networks and Communications
  • Urban Studies
  • Control and Systems Engineering

Cite this

Khan, I., Al Sadiri, A., Ahmad, A. R., & Jabeur, N. (2019). Tracking student performance in introductory programming by means of machine learning. In 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019 [8645608] (2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICBDSC.2019.8645608
Khan, Ijaz ; Al Sadiri, Abir ; Ahmad, Abd Rahim ; Jabeur, Nafaa. / Tracking student performance in introductory programming by means of machine learning. 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019).
@inproceedings{590246527a0f4119abf8437346d0a5bd,
title = "Tracking student performance in introductory programming by means of machine learning",
abstract = "large amount of digital data is being generated across a wide variety of fields and Data Mining (DM) techniques are used transform it into useful information so as to identify hidden patterns. One of the key areas of the application of Education Data Mining (EDM) is the development of student performance prediction models that would predict the student's performance in educational institutions. We build a model which can notify students (in introductory programming course) about their probable outcomes at an early stage of the semester (when evaluated for 15{\%} grades). We applied 11 Machine Learning algorithms (from 5 categories) over a data source using WEKA and concluded that Decision Tree (J48) is giving higher accuracy in terms of correctly identified instances, F-Measure rate and true positive detections. This study will help to the students to identify their probable final grades and modify their academic behavior accordingly to achieve higher grades.",
author = "Ijaz Khan and {Al Sadiri}, Abir and Ahmad, {Abd Rahim} and Nafaa Jabeur",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/ICBDSC.2019.8645608",
language = "English",
series = "2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019",
address = "United States",

}

Khan, I, Al Sadiri, A, Ahmad, AR & Jabeur, N 2019, Tracking student performance in introductory programming by means of machine learning. in 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019., 8645608, 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019, Institute of Electrical and Electronics Engineers Inc., 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019, Muscat, Oman, 15/01/19. https://doi.org/10.1109/ICBDSC.2019.8645608

Tracking student performance in introductory programming by means of machine learning. / Khan, Ijaz; Al Sadiri, Abir; Ahmad, Abd Rahim; Jabeur, Nafaa.

2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8645608 (2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Tracking student performance in introductory programming by means of machine learning

AU - Khan, Ijaz

AU - Al Sadiri, Abir

AU - Ahmad, Abd Rahim

AU - Jabeur, Nafaa

PY - 2019/2/19

Y1 - 2019/2/19

N2 - large amount of digital data is being generated across a wide variety of fields and Data Mining (DM) techniques are used transform it into useful information so as to identify hidden patterns. One of the key areas of the application of Education Data Mining (EDM) is the development of student performance prediction models that would predict the student's performance in educational institutions. We build a model which can notify students (in introductory programming course) about their probable outcomes at an early stage of the semester (when evaluated for 15% grades). We applied 11 Machine Learning algorithms (from 5 categories) over a data source using WEKA and concluded that Decision Tree (J48) is giving higher accuracy in terms of correctly identified instances, F-Measure rate and true positive detections. This study will help to the students to identify their probable final grades and modify their academic behavior accordingly to achieve higher grades.

AB - large amount of digital data is being generated across a wide variety of fields and Data Mining (DM) techniques are used transform it into useful information so as to identify hidden patterns. One of the key areas of the application of Education Data Mining (EDM) is the development of student performance prediction models that would predict the student's performance in educational institutions. We build a model which can notify students (in introductory programming course) about their probable outcomes at an early stage of the semester (when evaluated for 15% grades). We applied 11 Machine Learning algorithms (from 5 categories) over a data source using WEKA and concluded that Decision Tree (J48) is giving higher accuracy in terms of correctly identified instances, F-Measure rate and true positive detections. This study will help to the students to identify their probable final grades and modify their academic behavior accordingly to achieve higher grades.

UR - http://www.scopus.com/inward/record.url?scp=85063188659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063188659&partnerID=8YFLogxK

U2 - 10.1109/ICBDSC.2019.8645608

DO - 10.1109/ICBDSC.2019.8645608

M3 - Conference contribution

T3 - 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019

BT - 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Khan I, Al Sadiri A, Ahmad AR, Jabeur N. Tracking student performance in introductory programming by means of machine learning. In 2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8645608. (2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019). https://doi.org/10.1109/ICBDSC.2019.8645608