Skip to content
Open access

EduVa: Prototyping and testing AI-powered interactive LMS with adaptive modules and assessments

Aug 2026 · Indonesian Journal of Educational Development · Vol 7, pp. 553-569 · 0 citations

TL;DR

The findings demonstrate that the EduVa LMS is valid, usable, and effective for implementing adaptive learning, and shows a strong correlation between AI assessments and learning objectives.

Abstract

The rapid integration of artificial intelligence (AI) in higher education has increased the demand for adaptive Learning Management Systems (LMS) capable of delivering personalized learning at scale. However, empirical studies covering the full lifecycle of designing, prototyping, and testing AI-powered LMS remain limited, particularly in developing regions. This study aimed to design, prototype, and test EduVa LMS (Education Virtual Assistant), an AI-powered interactive LMS with adaptive modules and AI-driven assessments, implemented across ten private universities in East Nusa Tenggara, Indonesia. A Design Science Research (DSR) approach integrated with the ADDIE model guided the development process. A total of 360 participants were involved, including experts, students, and lecturers. Validation results showed a Content Validity Index (CVI) of 0.80, confirming content validity. Usability testing using the System Usability Scale (SUS) yielded mean scores of 82.4 (students) and 85.8 (lecturers). Adaptive performance analysis indicated 82.1% assessment accuracy, 3.7 content adjustments per session, and an 87.9% completion rate. A strong correlation (r = 0.81, p < .01) was found between AI assessments and learning objectives. The findings demonstrate that the EduVa LMS is valid, usable, and effective for implementing adaptive learning.

Read PDF

Similar papers

Open access 2026

Assessing Student Needs for AI-based Adaptive Learning in Higher Education

The study contributes user-derived design requirements that can guide the development of trustworthy and context-appropriate AI-supported learning platforms for undergraduate ICT students in programming-related courses at the two participating universities; broader generalization to other higher education fields requires further research.

Кazimova Dinara, Turmuratova Dinara, Zatyneyko Anatoly et al. · 0 citations
Review Open access 2026

Design and Evaluation of an AI-Based E-Learning System for Graduate Education

Findings indicate that AI-based e-learning enhances personalization, engagement, and data-driven learning in higher education.

Ngatmini Ngatmini, Baharuddin Baharuddin, Mansur As et al. · 0 citations
Open access Aug 2026

The AI Playground: A Universal Design for Learning Approach to AI Education in Engineering

The use of artificial intelligence (AI) is becoming more prevalent in all fields, especially in engineering, yet most students still have limited capabilities in terms of proper engagement with AI tools. This paper introduces a new initiative, called the AI Playground, designed to include AI education directly into the engineering curricula using a Universal Design for Learning (UDL) approach. The aim is to provide every participant no matter their background or level of education, the ability to explore AI concepts and practice problem solving with Large Language Models (LLMs), while using AI as an aid for research, coursework and industrial applications. The AI Playground was developed iteratively over one year based on community feedback, with evaluation conducted through tracking workshop attendance and participant engagement across multiple delivery styles. The initiative grew to 82 participants predominantly undergraduate engineering students, who reported that community-based learning helped them integrate AI literacy productively into their coursework. The findings demonstrate that a UDL-based, community oriented approach creates an accessible and inclusive pathway for engineering students to develop AI competence and ethical awareness.

Mert Sehri, K. Hakkõ, P. Dumond · 0 citations
Open access Aug 2026

Developing AI Enhanced Gamified Assessments to Improve Student Mastery of English Tense

The integration of Artificial Intelligence (AI) with gamified learning platforms demonstrates strong potential to enhance student engagement and improve learning outcomes in English language education. This study aims to develop and evaluate AI-supported gamified assessments focusing on students’ mastery of English verb tenses, including Simple Present, Simple Past, and Simple Future. The research employed a Research and Development (R&D) approach using the ADDIE model, which consists of Analysis, Design, Development, Implementation, and Evaluation stages. The study was conducted at Institut Teknologi dan Bisnis Asia Malang involving undergraduate EFL students. The learning tool was developed through the Wayground (Quizizz) platform and supported by AI features such as adaptive feedback, randomized questions, and automated performance monitoring. Validation was carried out by media and subject-matter experts using Likert-scale questionnaires to ensure pedagogical and technical quality. The implementation results showed that 87% of students achieved the expected learning outcomes. These outcomes included the ability to accurately identify, analyse, and apply English tenses in various grammatical and communicative contexts. In addition, students demonstrated increased participation, greater learning motivation, and improved confidence when completing grammar-related tasks. The findings indicate that AI-enhanced gamified assessments effectively support grammar instruction by promoting learner autonomy, improving comprehension, and creating a more engaging learning environment. Therefore, the integration of AI-powered gamified assessments can serve as an innovative and effective approach to enhancing English grammar learning in higher education EFL contexts.

Widya Adhariyanty Rahayu, Jaenal Arifin · 0 citations
Open access Aug 2026

Development of Interactive Learning Multimedia for Primary Science Education: An Alessi and Trollip Model Approach

Low learning outcomes in Natural and Social Sciences (IPAS) among fourth-grade students at SD Negeri 14 OKU prompted this study. The predominance of conventional teaching methods and inadequate use of interactive learning media had led to monotonous learning conditions, reduced student engagement, and less meaningful educational experiences. This study aimed to develop PowerPoint-based interactive learning multimedia for fourth-grade IPAS instruction that meets the criteria of validity and practicality as judged by expert validation and student response data. A Research and Development (R&D) method was employed, guided by the Alessi and Trollip instructional design model and Tessmer's formative evaluation framework. The development stages encompassed planning, design, production, expert validation, and sequential field trials including one-to-one evaluation, small group evaluation, and field testing. Data were gathered through expert validation sheets and student response questionnaires. Results indicated that the developed multimedia achieved strong feasibility levels: media expert validation reached 87.5%, materials expert validation 88.2%, and instructional design expert validation 84.4%, yielding an overall average of 86.7% (Excellent category). Student trial outcomes showed progressive improvement in perceived practicality: 85.6% in one-to-one evaluation, 87.6% in small group evaluation, and 89.4% in field testing, all within the good-to-excellent range. These findings confirm that the PowerPoint-based interactive learning multimedia is valid and practical, and shows strong promise for supporting student engagement and perceived comprehension in IPAS at the elementary school level. Future research employing pre-test and post-test designs is recommended to provide stronger evidence of direct learning outcome gains.

Partini, Leni Febriantika, Heni Rita Susila · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.