Utilizando Question Answering no Auxílio ao Processo de Ensino e Aprendizagem de Programação: Um Estudo de Caso com BERT e ChatGPT

Abstract

Natural Language Processing is an area of Artificial Intelligence that has brought benefits to the most diverse processes of human activity. In this context, this work uses a Question Answering (QA) approach to help in the process of teaching and learning programming. For this purpose, it analyzed two case studies with different QA models and a database with 87 questions and answers related to teaching programming. Thus, the models achieved 62% and 85% accuracy in the first and second scenarios, respectively. The present work also discusses (i) some limitations of the approach, (ii) some qualitative pedagogical results, and, finally, indicates (iii) recommendations for future work.