Interventions in STEM Education Through Speech Recognition-Based Learning Analysis

Abstract

This study uses a quasi-experimental design to explore the role of natural language processing (NLP) and speech recognition technologies in supporting teacher interventions during collaborative STEM activities. The Speech Recognition Keywords Analysis System (SRKAS) was developed to extract keywords from student discussions, enabling real-time monitoring and timely teacher support. The study compares proactive and passive interventions, focusing on their effects on student engagement, anxiety, and confidence. Results show that proactive interventions enhance engagement, reduce anxiety, and increase confidence by providing immediate assistance. These findings highlight the value of technology-enhanced teaching strategies in collaborative learning and offer insights for improving student outcomes in STEM education.