Claim Missing Document
Check
Articles

Found 33 Documents
Search

Implementation of Machine Learning as Interactive Media in Modern Computer Learning Jenny Sari Tarigan; Erwinsyah Simanungkalit; Mardhiatul Husna; Djames Siahaan
International Journal of Educational Narratives Vol. 4 No. 1 (2026)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijen.v4i1.3447

Abstract

Background. This study explores the use of machine learning as an interactive medium in the context of modern computer learning, driven by increasingly dynamic educational demands that require adaptive and personalized learning approaches. Purpose. This study aims to evaluate the effectiveness of machine learning algorithms in developing interactive learning media that can improve conceptual understanding, active student participation, and a more personalized learning experience. Method. The methodology used is qualitative with a case study and experimental design, including observations, interviews with instructors and students, and quantitative and qualitative data analysis of system interactions. Results. The research findings indicate that learning media integrated with machine learning can adapt material to students' abilities and learning styles, provide real-time feedback, and increase student motivation and engagement in the learning process. The discussion highlights that machine learning functions not only as a technological tool but also as a means of pedagogical transformation that delivers an adaptive and personalized learning experience. Conclusion. Thus, the implementation of machine learning as an interactive medium has proven effective in improving the quality of the teaching-learning process, encouraging active participant engagement, and adapting materials to individual needs, making it an important strategy in modern, responsive computer education.  
Narratives of Performance Assessment-Based Competency Testing for Measuring Students' Programming Competencies Erwinsyah Simanungkalit; Jenny Sari Taringan; Mardhiatul Husna; Djames Siahaan
International Journal of Educational Narratives Vol. 4 No. 3 (2026)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijen.v4i3.3510

Abstract

Background. Programming competence is a fundamental skill for students in information technology education. Despite its importance, assessment practices continue to rely predominantly on theoretical examinations that inadequately represent students’ practical abilities to solve authentic programming problems. Purpose. This study aims to explore the narratives of performance assessment-based competency testing for measuring students’ programming competencies through an authentic and comprehensive assessment model that captures both learning processes and performance outcomes. Method. This study employed a quantitative approach using a quasi-experimental design supported by a literature review. Performance assessment narratives were developed from students’ competency test results using a structured rubric encompassing four dimensions: algorithm planning, code implementation, debugging, and program optimization. Results. The findings reveal narratives of students’ programming competency development that are more comprehensive than those generated through conventional assessment methods. The performance assessment model demonstrated greater accuracy in evaluating authentic programming competencies. Students achieved the highest performance in code implementation, whereas debugging and program optimization emerged as the primary challenges. Furthermore, the assessment narratives provided deeper insights into students’ critical thinking, problem-solving abilities, creativity, and the progression of their programming skills.   Conclusion. he narratives generated through performance assessment-based competency testing offer an authentic and effective evaluation framework for measuring students’ programming competencies. Beyond providing reliable evidence of learning outcomes, these narratives deliver meaningful feedback that supports continuous competency development and better prepares students to meet the professional demands of the information technology industry.
Teaching the Machine, Narrating the Self: Teachers’ Lived Experiences in Implementing IoT-Based Transformative Learning Arfanda Anugrah Siregar; Tongam E Panggabean; Erwinsyah Simanungkalit; Muhammad Hizbullah Rais Siregar
International Journal of Educational Narratives Vol. 4 No. 2 (2026)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijen.v4i2.3648

Abstract

Background. Gas leaks in households pose severe risks of explosion and poisoning. Conventional detection methods often lack the responsiveness required for early prevention, necessitating more modern, IoT-based monitoring systems. Purpose. This study aims to develop and evaluate an IoT-based learning model through a gas leak detection system integrated with Telegram API to enhance both environmental safety and student digital literacy. Method. This experimental research was conducted over a sixteen-week period. The system was designed using an MQ-2 gas sensor and a NodeMCU ESP8266 microcontroller. The methodology involved four stages: system design, device implementation, performance testing across varying gas concentrations (120–800 ppm), and pedagogical evaluation of the learning model's impact on students' technical competencies. Results. Technical testing demonstrated that the system is highly responsive, with an average notification delay of 2 to 5 seconds depending on gas density. At dangerous levels (600–800 ppm), the system consistently achieved a rapid 2-second response time with a 100% notification success rate via Telegram. Conclusion. The study’s novelty lies in its dual-purpose framework, which functions not only as a high-precision safety tool but also as a structured pedagogical medium that bridges the gap between theoretical IoT concepts and practical environmental responsibility.