Predicting Computer Science Student Motivation Using Multisource Data

Hafsa Al Ansari; Rasha S. Al Jassim; Rupert Ward

doi:10.1109/ICCIAA65327.2025.11013026

Predicting Computer Science Student Motivation Using Multisource Data

Hafsa Al Ansari, Rasha S. Al Jassim, Rupert Ward

University of Technology and Applied Sciences (Suhar)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this study, a new framework will be developed to predict student motivation types using data from a survey and learning management system (LMS). As part of this framework, this research proposes the use of the XGBoost model to enhance prediction accuracy and identify key influencing factors. The findings demonstrate the excellent predictive capability of the XGBOOST model, achieving accuracy ranging between 95% and 100% across different datasets. Additionally, the study reveals the different learning analytics(LA) features associated with different motivation types. These features can be used to improve students' academic journeys and offer personalized learning experiences. While this framework is designed specifically for predicting student motivation, its adaptability allows it to be applied in other domains.

Original language	English
Title of host publication	2025 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	7
ISBN (Electronic)	9798331523657
ISBN (Print)	9798331523664
DOIs	https://doi.org/10.1109/ICCIAA65327.2025.11013026
Publication status	Published - 2 Jun 2025
Event	1st International Conference on Computational Intelligence Approaches and Applications - Amman, Jordan Duration: 28 Apr 2025 → 30 Apr 2025 https://uop.edu.jo/En/ICCIAA/Pages/default.aspx

Conference

Conference	1st International Conference on Computational Intelligence Approaches and Applications
Abbreviated title	ICCIAA 2025
Country/Territory	Jordan
City	Amman
Period	28/04/25 → 30/04/25
Internet address	https://uop.edu.jo/En/ICCIAA/Pages/default.aspx

Access to Document

10.1109/ICCIAA65327.2025.11013026Licence: Unspecified

Cite this

@inproceedings{ed3ffd64b6f34dafb05a25a6b4d074f2,

title = "Predicting Computer Science Student Motivation Using Multisource Data",

abstract = "In this study, a new framework will be developed to predict student motivation types using data from a survey and learning management system (LMS). As part of this framework, this research proposes the use of the XGBoost model to enhance prediction accuracy and identify key influencing factors. The findings demonstrate the excellent predictive capability of the XGBOOST model, achieving accuracy ranging between 95\% and 100\% across different datasets. Additionally, the study reveals the different learning analytics(LA) features associated with different motivation types. These features can be used to improve students' academic journeys and offer personalized learning experiences. While this framework is designed specifically for predicting student motivation, its adaptability allows it to be applied in other domains.",

keywords = "Machine Learning in Education, Motivation, Prediction, XGBoost",

author = "\{Al Ansari\}, Hafsa and \{Al Jassim\}, \{Rasha S.\} and Rupert Ward",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 ; Conference date: 28-04-2025 Through 30-04-2025",

year = "2025",

month = jun,

day = "2",

doi = "10.1109/ICCIAA65327.2025.11013026",

language = "English",

isbn = "9798331523664",

booktitle = "2025 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

url = "https://uop.edu.jo/En/ICCIAA/Pages/default.aspx",

}

Al Ansari, H, Al Jassim, RS & Ward, R 2025, Predicting Computer Science Student Motivation Using Multisource Data. in 2025 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 - Proceedings., 11013026, Institute of Electrical and Electronics Engineers Inc., 1st International Conference on Computational Intelligence Approaches and Applications, Amman, Jordan, 28/04/25. https://doi.org/10.1109/ICCIAA65327.2025.11013026

Predicting Computer Science Student Motivation Using Multisource Data. / Al Ansari, Hafsa; Al Jassim, Rasha S.; Ward, Rupert.
2025 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. 11013026.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Predicting Computer Science Student Motivation Using Multisource Data

AU - Al Ansari, Hafsa

AU - Al Jassim, Rasha S.

AU - Ward, Rupert

PY - 2025/6/2

Y1 - 2025/6/2

N2 - In this study, a new framework will be developed to predict student motivation types using data from a survey and learning management system (LMS). As part of this framework, this research proposes the use of the XGBoost model to enhance prediction accuracy and identify key influencing factors. The findings demonstrate the excellent predictive capability of the XGBOOST model, achieving accuracy ranging between 95% and 100% across different datasets. Additionally, the study reveals the different learning analytics(LA) features associated with different motivation types. These features can be used to improve students' academic journeys and offer personalized learning experiences. While this framework is designed specifically for predicting student motivation, its adaptability allows it to be applied in other domains.

AB - In this study, a new framework will be developed to predict student motivation types using data from a survey and learning management system (LMS). As part of this framework, this research proposes the use of the XGBoost model to enhance prediction accuracy and identify key influencing factors. The findings demonstrate the excellent predictive capability of the XGBOOST model, achieving accuracy ranging between 95% and 100% across different datasets. Additionally, the study reveals the different learning analytics(LA) features associated with different motivation types. These features can be used to improve students' academic journeys and offer personalized learning experiences. While this framework is designed specifically for predicting student motivation, its adaptability allows it to be applied in other domains.

KW - Machine Learning in Education

KW - Motivation

KW - Prediction

KW - XGBoost

UR - https://www.scopus.com/pages/publications/105010153757

U2 - 10.1109/ICCIAA65327.2025.11013026

DO - 10.1109/ICCIAA65327.2025.11013026

M3 - Conference contribution

AN - SCOPUS:105010153757

SN - 9798331523664

BT - 2025 1st International Conference on Computational Intelligence Approaches and Applications, ICCIAA 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st International Conference on Computational Intelligence Approaches and Applications

Y2 - 28 April 2025 through 30 April 2025

ER -

Predicting Computer Science Student Motivation Using Multisource Data

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this