Application of ADDIE Instructional Model to Machine Learning and Assessment of Learner’s Outcomes in Higher Institutions in Delta State

Aug 3, 2026

Upload by Riley

The study explored the application of the ADDIE instructional model to machine learning and the assessment of learner outcomes in higher institutions in Delta State. A pretest, posttest control group quasi-experimental design was adopted with experimental and control groups. The ADDIE model guided the design and implementation of a machine learning course, while two validated instruments—the ETAT and MLQ—measured outcomes. Reliability was confirmed via Kuder-Richardson 21 and Cronbach Alpha (0.71, 0.78). Results indicated improved learning outcomes and more effective assessment, supported by a six-week treatment. Training for educators and sharing best practices were recommended.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Machine learning overview

Types of machine learning

Challenges and solutions

e-ISSN 2795-3272 p-ISSN 2795-3264 10.5281/zenodo.14258782 Vol. 07 Issue 10 Oct-2024 Manuscript ID: \#01651 Application of ADDIE Instructional Model to Machine Learning and Assessment of Learner’s Outcomes in Higher Institutions in Delta State Iroriteraye-Adjekpovu, Janice Imizuokena (Ph.D) Department of Science Education, Delta State University, Abraka. Abstract The study explored the application of the ADDIE instructional model to machine learning and the assessment of learner's outcomes in higher institutions in Delta State. The study adopted pretest, posttest control group quasi-experimental design. The design comprised of two groups, experimental and control group. In this study, the researcher applied the ADDIE model to the design and implementation of a machine learning course and assess the outcomes of learners using various assessment methods. The population for the study comprised 3,478 300level undergraduate in Delta State University, Abraka and University of Delta, Agbor. The sample of the study comprised 139 300level undergraduates in Delta State University, Abraka and University of Delta, Agbor. Educational Technology Achievement Test (ETAT) and Machine Learning Questionnaire (MLQ) were used for data collection. The two instruments were duly validated. The reliability of ETAT and MLQ were established using Kuder-Richardson 21 and Cronbach Alpha analysis respectively. A reliability coefficient of 0.71 and 0.78, were obtained for ETAT and MLQ respectively. ETAT was administered as pretest and posttest before and after a six weeks treatment using ADDIE and traditional instructional models to students in experimental and control groups respectively. MLQ was only administered at the end of the treatment. Findings showed that ADDIE model provided a structured framework for designing, developing, and evaluating machine learning courses, leading to improved learning outcomes for students. The assessment of learner's outcomes has also been more effective and efficient with the implementation ofthe ADDIE model. It was recommended that higher institutions in Delta State should provide training and capacity building for educators on how to effectively implement the ADDIE instructional model in machine learning courses. Educators should collaborate and share best practices in the application of the ADDIE model to machine learning to enhance teaching and learning outcomes. Keywords: ADDIE Instructional Model, Machine Learning, Learner’s Outcome, Assessment. How to cite: Janice Imizuokena, I. -A. (2024). Application of ADDIE Instructional Model to Machine Learning and Assessment of Learner’s Outcomes in Higher Institutions in Delta State. GPH-International Journal of Educational Research, 7(10), 98-109. [https://doi.org/10.5281/zenodo.14258782](https://doi.org/10.5281/zenodo.14258782) This work is licensed under Creative Commons Attribution 4.0 License. Page 98 of 109 Introduction Machine learning is a branch of artificial intelligence that concentrates on creating algorithms and statistical models to enable computers to learn and make predictions or judgements without explicit programming. The field is experiencing significant growth and has diverse applications across several industries, such as healthcare, finance, marketing, and others. Machine learning has gained popularity in recent years because of its capacity to analyse vast quantities of data and derive significant insights. A fundamental characteristic of machine learning is its capacity to enhance performance over time by using data (Jordan & Mitchell, 2015) . Through the process of inputting substantial quantities of data into a machine learning algorithm, the system can acquire knowledge from the patterns and trends within the data, enabling it to provide predictions or make informed judgments. The process referred to as training is crucial for the algorithm to achieve optimal performance on unfamiliar data. LeCun et al. (2015) categoris

FAQs

What instructional approach did the study apply to machine learning course design?

The study applied the ADDIE instructional model to the design and implementation of a machine learning course for higher institutions in Delta State.

How were learner outcomes assessed in the quasi-experimental design?

Learner outcomes were assessed using the Educational Technology Achievement Test (ETAT) with pretest and posttest, and the Machine Learning Questionnaire (MLQ) administered at the end of the treatment.

What did the findings indicate about ADDIE’s impact?

The findings showed that ADDIE provided a structured framework for designing, developing, and evaluating the machine learning course, leading to improved learning outcomes and more effective assessment of learner outcomes.

Aug 3, 2026

Upload by Riley