JIITA, vol.7 no.3, p.763-769 2023, DOI: 10.22664/ISITA.2023.7.3.769
Hyeonji Kim, Yoosoo Oh
Abstract: Children with developmental disabilities communicate through speech and actions. However, children with developmental disabilities have difficulty communicating their feelings to others using language. Nevertheless, children with developmental disabilities express their emotions primarily through words rather than actions. Therefore, this paper proposes a mixing model that combines SEBRT, a language embedding model, and Voting Classifier, a machine learning ensemble model. The proposed mixture model can improve the performance of sentiment analysis models for developmentally disabled children by not only sentence embedding but also by giving them semantic weights.
Keywords: Developmentally disabled children, NLP, SBERT, Machine Learning, Ensemble Learning
Fullpaper: