Adapting Knowledge Inference Algorithms to Measure Geometry Competencies through a Puzzle Game

Strukova, Sofia; Gómez Mármol, Félix; Ruipérez Valiente, José Antonio

Publication:
Adapting Knowledge Inference Algorithms to Measure Geometry Competencies through a Puzzle Game

dc.contributor.author	Strukova, Sofia
dc.contributor.author	Gómez Mármol, Félix
dc.contributor.author	Ruipérez Valiente, José Antonio
dc.contributor.department	Ingeniería de la Información y las Comunicaciones
dc.date.accessioned	2025-01-23T11:19:34Z
dc.date.available	2025-01-23T11:19:34Z
dc.date.issued	2023-09-06
dc.description	© 2023 Los autores This document is the accepted version of a published work that appeared in final form in ACM Transactions on Knowledge Discovery from Data This document is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0 To access the final edited and published work see: https://doi.org/10.1145/3614436
dc.description.abstract	The rapid technological evolution of the last years has motivated students to develop capabilities that will prepare them for an unknown future in the 21st century. In this context, many teachers intend to optimise the learning process, making it more dynamic and exciting through the introduction of gamification. Thus, this article focuses on a data-driven assessment of geometry competencies, which are essential for developing problem-solving and higher-order thinking skills. Our main goal is to adapt, evaluate and compare Bayesian Knowledge Tracing (BKT), Performance Factor Analysis (PFA), Elo, and Deep Knowledge Tracing (DKT) algorithms applied to the data of a geometry game named Shadowspect, in order to predict students’ performance by means of several classifier metrics. We analysed two algorithmic configurations, with and without prioritisation of Knowledge Components (KCs) – the skills needed to complete a puzzle successfully, and we found Elo to be the algorithm with the best prediction power with the ability to model the real knowledge of students. However, the best results are achieved without KCs because it is a challenging task to differentiate between KCs effectively in game environments. Our results prove that the above-mentioned algorithms can be applied in formal education to improve teaching, learning, and organisational efficiency.	es
dc.format	application/pdf	es
dc.format.extent	24	es
dc.identifier.citation	ACM Transactions on Knowledge Discovery from Data, Volume 18, Issue 1 Article No.: 21, Pages 1 - 23
dc.identifier.doi	https://doi.org/10.1145/3614436
dc.identifier.issn	Print.:1556-4681
dc.identifier.issn	Electronic.: 1556-472X
dc.identifier.uri	http://hdl.handle.net/10201/149146
dc.language	eng	es
dc.publisher	ACM	es
dc.relation	Sin financiación externa a la Universidad	es
dc.rights	info:eu-repo/semantics/openAccess	es
dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 Internacional	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/	*
dc.subject	Computational social science	es
dc.subject	Data-driven evaluation	es
dc.subject	Data mining	es
dc.subject	Competencies	es
dc.subject	Capabilities	es
dc.title	Adapting Knowledge Inference Algorithms to Measure Geometry Competencies through a Puzzle Game	es
dc.type	info:eu-repo/semantics/article	es
dspace.entity.type	Publication	es
relation.isAuthorOfPublication	a34140f9-361d-448f-a0b9-850b55fa20b3
relation.isAuthorOfPublication.latestForDiscovery	a34140f9-361d-448f-a0b9-850b55fa20b3