Learner Differences in Hint Processing [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (5th, Chania, Greece, Jun 19-21, 2012).

Autor/inn/en	Goldin, Ilya M.; Koedinger, Kenneth R.; Aleven, Vincent
Institution	International Educational Data Mining Society
Titel	Learner Differences in Hint Processing [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (5th, Chania, Greece, Jun 19-21, 2012).
Quelle	(2012), (8 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Performance Factors; Intelligent Tutoring Systems; Individual Differences; Prediction; Probability; Regression (Statistics); Geometry; Bayesian Statistics; Item Response Theory; Correlation; Problem Solving + Suchen Sie Ihr Suchwort? Leistungsindikator; Intelligentes Tutorsystem; Individueller Unterschied; Vorhersage; Wahrscheinlichkeitsrechnung; Wahrscheinlichkeitstheorie; Regression; Regressionsanalyse; Geometrie; Item-Response-Theorie; Korrelation; Problemlösen
Abstract	Although ITSs are supposed to adapt to differences among learners, so far, little attention has been paid to how they might adapt to differences in how students learn from help. When students study with an Intelligent Tutoring System, they may receive multiple types of help, but may not comprehend and make use of this help in the same way. To measure the extent of such individual differences, we propose two new logistic regression models, ProfHelp and ProfHelp-ID. Both models extend the Performance Factors Analysis model (Pavlik, Cen & Koedinger, 2009) with parameters that represent the effect of hints on performance on the same step on which the help was given. Both models adjust for general student proficiency, prior practice on knowledge components, and knowledge component difficulty. Multilevel Bayesian implementations of these models were fit to data on student interactions with a geometry ITS, where students received on-demand problem-relevant help ranging from first-level hints that facilitate application of principles to specific and immediately actionable bottom-out hints. The model comparison showed that in this dataset students differ in their individual hint-processing proficiency and these differences depend on hint levels. These results suggest that we can assess specific learning skills, e.g., making sense of instructional text, and in future work we may be able to remediate and improve such skills. (Contains 2 figures, 4 tables, and 5 footnotes.) [For the complete proceedings, "Proceedings of the International Conference on Educational Data Mining (EDM) (5th, Chania, Greece, June 19-21, 2012)," see ED537074.] (As Provided).
Anmerkungen	International Educational Data Mining Society. e-mail: admin@educationaldatamining.org; Web site: http://www.educationaldatamining.org
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10