A method for automated generation of exercises with similar level of complexity

  • João Mendes UFRN
  • João Marcos UFRN

Resumo


The effort put by an educator on the manual construction of questions may be reduced if one uses tools for the automated generation of questions. Among these tools, only very few are able to control the level of complexity of their output, which ends up representing a challenge for the dissemination of individualized assessments. In the present study, we propose a method for the automated generation of exercises which uses the structure of the solution for the conjecture given as input in order to guarantee the similarity in the level of complexity of these exercises.

Referências

D’Agostino, M. (1999). Tableau Methods for Classical Propositional Logic, pages 45–123. Springer Netherlands, Dordrecht.

Kurdi, G., Leo, J., Parsia, B., Sattler, U., and Al-Emari, S. (2020). A systematic review of automatic question generation for educational purposes. International Journal of Artificial Intelligence in Education, 30(1):121–204.

Manoharan, S. (2017). Personalized assessment as a means to mitigate plagiarism. IEEE Transactions on Education, 60(2):112–119.

Millar, R. and Manoharan, S. (2021). Repeat individualized assessment using isomorphic questions: a novel approach to increase peer discussion and learning. International Journal of Educational Technology in Higher Education, 18(1):22.

Singhal, R., Goyal, S., and Henz, M. (2016). User-defined difficulty levels for automated question generation. In 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), pages 828–835.

Wang, K. and Su, Z. (2016). Dimensionally guided synthesis of mathematical word problems. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, page 2661–2668. AAAI Press.
Publicado
06/08/2023
MENDES, João; MARCOS, João. A method for automated generation of exercises with similar level of complexity. In: WORKSHOP BRASILEIRO DE LÓGICA (WBL), 4. , 2023, João Pessoa/PB. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 17-24. ISSN 2763-8731. DOI: https://doi.org/10.5753/wbl.2023.230660.