Autistic children communicate through speech and actions. Children with autism express their emotions primarily through words rather than actions. Therefore, this paper proposes a mixing model that combines Sentence-BERT as a language embedding model and Voting Classifier as a machine learning ensemble model. The proposed mixture model can improve the performance of sentiment analysis models for autistic children by not only sentence embedding but also by giving them semantic weights. This paper proposes a model for the emotional analysis of children with autism in the future.

Autistic children, NLP, SBERT, Machine Learning, Ensemble Learning