Classifying behavior to elucidate elegant problem solving in an educational game

Laura Malkiewich, Ryan S. Baker, Valerie Shute, Shimin Kai, Luc Paquette

Research output: Contribution to conferencePaper

Abstract

Educational games have become hugely popular, and educational data mining has been used to predict student performance in the context of these games. However, models built on student behavior in educational games rarely differentiate between the types of problem solving that students employ and fail to address how efficacious student problem solutions are in game environments. Furthermore, few papers assess how the features selected for classification models inform an understanding of how student behaviors predict student performance. In this paper, we discuss the creation and consideration of two models that predict if a student will develop an elegant problem solution (the Gold model), or a non-optimal but workable solution (the Silver model), in the context of an educational game. A pre-determined set of features were systematically tested and fit into one or both of these models. The two models were then examined to understand how the selected features elucidate our understanding of student problem solving at varying levels of sophistication. Results suggest that while gaming the system and lack of persistence indicate non-optimal completion of a problem, gaining experience with a problem predicts more elegant problem solving. Results also suggest that general student behaviors are better predictors of student performance than level-specific behaviors.

Original languageEnglish (US)
Pages448-453
Number of pages6
StatePublished - Jan 1 2016
Event9th International Conference on Educational Data Mining, EDM 2016 - Raleigh, United States
Duration: Jun 29 2016Jul 2 2016

Conference

Conference9th International Conference on Educational Data Mining, EDM 2016
CountryUnited States
CityRaleigh
Period6/29/167/2/16

Fingerprint

Students
Data mining
Silver
Gold

Keywords

  • Classifiers
  • Educational games
  • Problem solving

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Malkiewich, L., Baker, R. S., Shute, V., Kai, S., & Paquette, L. (2016). Classifying behavior to elucidate elegant problem solving in an educational game. 448-453. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.

Classifying behavior to elucidate elegant problem solving in an educational game. / Malkiewich, Laura; Baker, Ryan S.; Shute, Valerie; Kai, Shimin; Paquette, Luc.

2016. 448-453 Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.

Research output: Contribution to conferencePaper

Malkiewich, L, Baker, RS, Shute, V, Kai, S & Paquette, L 2016, 'Classifying behavior to elucidate elegant problem solving in an educational game' Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States, 6/29/16 - 7/2/16, pp. 448-453.
Malkiewich L, Baker RS, Shute V, Kai S, Paquette L. Classifying behavior to elucidate elegant problem solving in an educational game. 2016. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.
Malkiewich, Laura ; Baker, Ryan S. ; Shute, Valerie ; Kai, Shimin ; Paquette, Luc. / Classifying behavior to elucidate elegant problem solving in an educational game. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.6 p.
@conference{906d05b23a4f4147b103fdba6b2bbdb1,
title = "Classifying behavior to elucidate elegant problem solving in an educational game",
abstract = "Educational games have become hugely popular, and educational data mining has been used to predict student performance in the context of these games. However, models built on student behavior in educational games rarely differentiate between the types of problem solving that students employ and fail to address how efficacious student problem solutions are in game environments. Furthermore, few papers assess how the features selected for classification models inform an understanding of how student behaviors predict student performance. In this paper, we discuss the creation and consideration of two models that predict if a student will develop an elegant problem solution (the Gold model), or a non-optimal but workable solution (the Silver model), in the context of an educational game. A pre-determined set of features were systematically tested and fit into one or both of these models. The two models were then examined to understand how the selected features elucidate our understanding of student problem solving at varying levels of sophistication. Results suggest that while gaming the system and lack of persistence indicate non-optimal completion of a problem, gaining experience with a problem predicts more elegant problem solving. Results also suggest that general student behaviors are better predictors of student performance than level-specific behaviors.",
keywords = "Classifiers, Educational games, Problem solving",
author = "Laura Malkiewich and Baker, {Ryan S.} and Valerie Shute and Shimin Kai and Luc Paquette",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "448--453",
note = "9th International Conference on Educational Data Mining, EDM 2016 ; Conference date: 29-06-2016 Through 02-07-2016",

}

TY - CONF

T1 - Classifying behavior to elucidate elegant problem solving in an educational game

AU - Malkiewich, Laura

AU - Baker, Ryan S.

AU - Shute, Valerie

AU - Kai, Shimin

AU - Paquette, Luc

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Educational games have become hugely popular, and educational data mining has been used to predict student performance in the context of these games. However, models built on student behavior in educational games rarely differentiate between the types of problem solving that students employ and fail to address how efficacious student problem solutions are in game environments. Furthermore, few papers assess how the features selected for classification models inform an understanding of how student behaviors predict student performance. In this paper, we discuss the creation and consideration of two models that predict if a student will develop an elegant problem solution (the Gold model), or a non-optimal but workable solution (the Silver model), in the context of an educational game. A pre-determined set of features were systematically tested and fit into one or both of these models. The two models were then examined to understand how the selected features elucidate our understanding of student problem solving at varying levels of sophistication. Results suggest that while gaming the system and lack of persistence indicate non-optimal completion of a problem, gaining experience with a problem predicts more elegant problem solving. Results also suggest that general student behaviors are better predictors of student performance than level-specific behaviors.

AB - Educational games have become hugely popular, and educational data mining has been used to predict student performance in the context of these games. However, models built on student behavior in educational games rarely differentiate between the types of problem solving that students employ and fail to address how efficacious student problem solutions are in game environments. Furthermore, few papers assess how the features selected for classification models inform an understanding of how student behaviors predict student performance. In this paper, we discuss the creation and consideration of two models that predict if a student will develop an elegant problem solution (the Gold model), or a non-optimal but workable solution (the Silver model), in the context of an educational game. A pre-determined set of features were systematically tested and fit into one or both of these models. The two models were then examined to understand how the selected features elucidate our understanding of student problem solving at varying levels of sophistication. Results suggest that while gaming the system and lack of persistence indicate non-optimal completion of a problem, gaining experience with a problem predicts more elegant problem solving. Results also suggest that general student behaviors are better predictors of student performance than level-specific behaviors.

KW - Classifiers

KW - Educational games

KW - Problem solving

UR - http://www.scopus.com/inward/record.url?scp=85057151696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057151696&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85057151696

SP - 448

EP - 453

ER -