Integrated Ai Wayground and Stad: Comprehensive Analysis of Student Motivation and Learning Outcomes

Abstract

The transformation of 21st-century education requires schools to improve quality while encouraging innovation through technology-supported learning. In economics classes, low student engagement and teacher-centered practices continue to hinder effective instruction. This study investigated how integrating the AI Wayground platform with the cooperative learning method STAD influences students’ motivation and learning outcomes. AI Wayground strengthened the STAD process by offering interactive digital tasks, automated feedback, adaptive learning paths that promoted collaboration, responsibility, and active participation. A quantitative approach was used, involving questionnaires, tests, observations, and documentation. Motivation was measured using items adapted from the Six-Factor FLLMQ, with 140 students selected randomly from a population of 544. Data processed using SPSS 25 showed strong effects through descriptive statistics, correlation, and multiple regression. The N-Gain score of 0.7898 (78%) indicated high effectiveness of the intervention. The combined influence of AI Wayground (X1) and STAD (X2) on learning outcomes (Y2) reached 94.5%, while an Adjusted R² of 0.805 showed that 81% of the variance was explained by both variables. T-test results (sig. 0.000 < 0.05) and the F-test value of 228.665 confirmed significant improvement. Descriptive data on motivation also supported these results. After the intervention, motivation increased markedly, with the mean rising to 92.32 and standard deviation decreasing to 2.20, indicating more consistent motivation across students. Median and mode scores of 93 showed generally high motivation, supported by positive kurtosis (3.81) and negative skewness (–2.25). Overall, integrating AI Wayground with STAD proved highly effective in boosting motivation and improving learning outcomes.