A Comparison of Machine Learning Algorithms for Predicting Student Performance in an Online Mathematics Game

Autor/inn/en	Lee, Ji-Eun; Jindal, Amisha; Patki, Sanika Nitin; Gurung, Ashish; Norum, Reilly; Ottmar, Erin
Titel	A Comparison of Machine Learning Algorithms for Predicting Student Performance in an Online Mathematics Game
Quelle	(2023), (16 Seiten) PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Lee, Ji-Eun) ORCID (Gurung, Ashish) ORCID (Ottmar, Erin) Weitere Informationen
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Teaching Methods; Algorithms; Mathematics Tests; Computer Games; Learning Analytics; Interaction Process Analysis; Middle School Students; Anxiety; Mathematics Instruction; Models; Validity; Algebra; Learning Processes; Computer Assisted Instruction; Comparative Analysis; Mathematical Concepts; Concept Formation; Sampling; Correlation; Scores; Prediction + Suchen Sie Ihr Suchwort? Teaching method; Lehrmethode; Unterrichtsmethode; Algorithm; Algorithmus; Computer game; Computerspiel; Computerspiele; Prozessanalyse; Middle school; Middle schools; Student; Students; Mittelschule; Mittelstufenschule; Schüler; Schülerin; Angst; Mathematics lessons; Mathematikunterricht; Analogiemodell; Gültigkeit; Learning process; Lernprozess; Computer based training; Computerunterstützter Unterricht; Concept learning; Begriffsbildung; Korrelation; Vorhersage
Abstract	This paper demonstrated how to apply Machine Learning (ML) techniques to analyze student interaction data collected in an online mathematics game. Using a data-driven approach, we examined: (1) how different ML algorithms influenced the precision of middle-school students' (N = 359) performance (i.e. posttest math knowledge scores) prediction; and (2) what types of in-game features (i.e. student in-game behaviors, math anxiety, mathematical strategies) were associated with student math knowledge scores. The results indicated that the Random Forest algorithm showed the best performance (i.e. the accuracy of models, error measures) in predicting posttest math knowledge scores among the seven algorithms employed. Out of 37 features included in the model, the validity of the students' first mathematical transformation was the most predictive of their posttest math knowledge scores. Implications for game learning analytics and supporting students' algebraic learning are discussed based on the findings. [This is the online first version of an article published in "Interactive Learning Environments."] (As Provided).
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01