EMOTION RECOGNITION IN LEARNERS WITH EMOJI SENTIMENT ACCOMPANIMENT USING THE PHOBERT MODEL

DOI: 10.18173/2354-1059.2024-0034

Tóm tắt

This paper proposes an advanced method for recognizing learners'emotions by incorporating the use of emojis to reflect the modern communicationtendencies of learners, typically young individuals. The method is built on thePhoBERT model, a variant of BERT optimized for Vietnamese. Data was collectedfrom opinion surveys of learners at the Ho Chi Minh City campus of the Universityof Transport and Communications to train and test the model. The system is designedto analyze text and recognize seven basic emotions: enjoyment, trust, hope, sadness,surprise, fear, and others. Corresponding emojis are then assigned to each emotiontype to more clearly illustrate the learners' emotional states. Experimental resultsshow that combining PhoBERT and emojis not only enhances the accuracy ofemotion recognition but also makes communication more intuitive and vivid. Themodel achieved an accuracy of 74.1%. The paper also discusses practicalapplications of this system in the field of education, where teachers can quickly andaccurately understand and respond to students' emotions, thereby improving teachingeffectiveness