Detalhes bibliográficos
| Ano de defesa: |
2019 |
| Autor(a) principal: |
Mainieri, Bruno Omella
 |
| Orientador(a): |
Omar, Nizam
|
| Banca de defesa: |
Não Informado pela instituição |
| Tipo de documento: |
Dissertação
|
| Tipo de acesso: |
Acesso aberto |
| Idioma: |
por |
| Instituição de defesa: |
Universidade Presbiteriana Mackenzie
|
| Programa de Pós-Graduação: |
Não Informado pela instituição
|
| Departamento: |
Não Informado pela instituição
|
| País: |
Não Informado pela instituição
|
| Palavras-chave em Português: |
|
| Área do conhecimento CNPq: |
|
| Link de acesso: |
http://dspace.mackenzie.br/handle/10899/24494
|
Resumo: |
In 2015, 53,1% of brazilian public schools thrid graders had inadequate knowledge of maths. Adaptive difficulty in educational games is proposed with the goal of maintaining adequate challenge for each player’s constantly evolving skill levels, thus promoting engagement and learning of the arithmetical operations of addition, subtraction and multiplication which are studied in this grade. In this research, two versions of an educational mathematics game were created - one of which possesses adaptive difficulty capabilities, and another which does not. The object was implemented according to definitions of motivational characteristics of games and assessment of different machine learning algorithms before being tested with third grade students. Results from this experiment suggest that the adaptive version of the game created greater engagement in users, with a 17,9% longer average interaction time compared to the non-adaptive version. Analysis of the players’ performance also indicates that the adaptive version was capable of offering a level of challenge more adequate to the users’ skills |
