Forecasting the performance of early childhood education childrens through a game-based learning approach

Autores

  • Gabriel Candido da Silva Universidade Federal Rural de Pernambuco
  • Rodrigo Lins Rodrigues Universidade Federal Rural de Pernambuco
  • Américo Nobre Amorim Escribo – Inovação para o Aprendizado
  • Amadeu Sá de Campos Filho Universidade Federal de Pernambuco

DOI:

https://doi.org/10.22456/1679-1916.137751

Palavras-chave:

Early years education, Serious games, Game learning analytics, Classification

Resumo

Currently, research that seeks to evaluate the learning acquired by players from a Serious Game has been adopting measures to demonstrate evidence collected in real-time. However, few studies seek to carry out this type of evaluation and techniques in Serious Games for early childhood education. That said, this study sought to apply a Game Learning Analytics process to assess at what level it is possible to predict the learning effect of 331 preschool childrens, based only on their interaction characteristics with 20 games that work on reading and writing skills, also showing which were the most effective interaction characteristics and classification techniques for this task. We found that errors in the games are the most relevant characteristic, and the Random Forest classifier is the most suitable for this experiment, rating a Precision of 82%.

Downloads

Não há dados estatísticos.

Downloads

Publicado

2023-12-31

Como Citar

SILVA, Gabriel Candido da; RODRIGUES, Rodrigo Lins; AMORIM, Américo Nobre; CAMPOS FILHO, Amadeu Sá de. Forecasting the performance of early childhood education childrens through a game-based learning approach. RENOTE, Porto Alegre, v. 21, n. 2, p. 297–306, 2023. DOI: 10.22456/1679-1916.137751. Disponível em: https://seer.ufrgs.br/index.php/renote/article/view/137751. Acesso em: 19 ago. 2026.

Edição

Seção

Jogos digitais aplicados ao ensino/aprendizagem