Affective Intervention Based on Learner Emotions for Online Learning in Video Conference Applications

Research on facial emotion recognition for learners has been conducted widely. However, research on how to deal with emotions detected during learning with computer systems has not been widely conducted. Therefore, this study aimed to develop a personalized verbal affective intervention through motivational messages to help learners regulate their negative emotions (sadness, anger, fear, and disgust). The system is developed for higher education learners on the Google Meet video conferencing application for online learning activities. The system was tested on 32 learners of Software Engineering at Universitas Pendidikan Indonesia. The learners were asked to fill out the Instructional Materials Motivation Survey (IMMS) questionnaire after the learning process to measure their learning motivation. Based on the questionnaire results, it can be concluded that personalized affective intervention, considering the ARCS Model, positively impacts learners’ motivation during synchronous online learning. This study suggests that a learning intervention based on the learner’s emotion recognition can positively affect the learner’s motivation and experience in using video conferencing apps during synchronous learning. This study can be a valuable reference for future research in implementing ARCS aspects that match learners’ emotional and emergent algorithms of affective interventions.