Expert system based chatbot for enhancing learning outcomes in kebaya analysis among vocational students

Abstract

This study aimed to determine the validity and effectiveness of an expert system-based chatbot as a learning medium for improving students' learning outcomes in kebaya garment analysis at a vocational high school. A quasi-experimental study employing a nonequivalent control group pretest–posttest design was conducted with 60 Grade XI Fashion Design students, divided equally into experimental and control groups. Data were collected using expert validation sheets, cognitive achievement tests, and perception questionnaires, and analyzed using Aiken's V, classical mastery, Normalized Gain (N-Gain), and an Independent Samples t-test. The chatbot demonstrated good validity (Aiken's V = 0.84). The experimental group achieved 100% classical mastery, a moderate N-Gain (0.57), and significantly higher posttest scores than the control group (p < 0.001). Teachers and students also reported positive perceptions (87.27% and 86.20%, respectively). The expert system-based chatbot is a valid and effective instructional medium that enhances learning outcomes and supports independent learning in vocational fashion education