Closing the Loop with Quantitative Cognitive Task Analysis [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (9th, Raleigh, NC, Jun 29-Jul 2, 2016).

Autor/inn/en	Koedinger, Kenneth R.; McLaughlin, Elizabeth A.
Titel	Closing the Loop with Quantitative Cognitive Task Analysis [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (9th, Raleigh, NC, Jun 29-Jul 2, 2016).
Quelle	(2016), (6 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Zusatzinformation	Weitere Informationen
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Educational Research; Data Collection; Task Analysis; Cognitive Processes; Models; Matrices; Middle School Students; Secondary School Mathematics; Algebra; Instructional Design; Mathematics Instruction; Mathematics Skills; Problem Solving; Difficulty Level + Suchen Sie Ihr Suchwort? Bildungsforschung; Pädagogische Forschung; Data capture; Datensammlung; Aufgabenanalyse; Cognitive process; Kognitiver Prozess; Analogiemodell; Matrizenrechnung; Middle school; Middle schools; Student; Students; Mittelschule; Mittelstufenschule; Schüler; Schülerin; Lesson concept; Lessonplan; Unterrichtsentwurf; Mathematics lessons; Mathematikunterricht; Mathmatics achievement; Mathematics ability; Mathematische Kompetenz; Problemlösen; Schwierigkeitsgrad
Abstract	Many educational data mining studies have explored methods for discovering cognitive models and have emphasized improving prediction accuracy. Too few studies have "closed the loop" by applying discovered models toward improving instruction and testing whether proposed improvements achieve higher student outcomes. We claim that such application is more effective when interpretable, explanatory models are produced. One class of such models involves a matrix mapping hypothesized (and typically human labeled) latent knowledge components (KCs) to the instructional practice tasks that require them. An under-investigated assumption in these models is that both task difficulty and learning transfer are modeled and predicted by the same latent KCs. We provide evidence for this assumption. More specifically, we investigate the data-driven hypothesis that competence with Algebra story problems may be better enhanced not through story problem practice but through, apparently task irrelevant, practice with symbolic expressions. We present new data and analytics that extend a prior close-the-loop study to 711 middle school math students. The results provide evidence that "quantitative cognitive task analysis" can use data from task difficulty differences to aid discovery of cognitive models that include non-obvious or hidden skills. In turn, student learning and transfer can be improved by closing the loop through instructional design of novel tasks to practice those hidden skills. [For the full proceedings, see ED592609.] (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	2020/1/01