Modelling the Way: Using Action Sequence Archetypes to Differentiate Learning Pathways from Learning Outcomes [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (9th, Raleigh, NC, Jun 29-Jul 2, 2016).

Autor/inn/en	Ng, Kelvin H. R.; Hartman, Kevin; Liu, Kai; Khong, Andy W. H.
Titel	Modelling the Way: Using Action Sequence Archetypes to Differentiate Learning Pathways from Learning Outcomes [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (9th, Raleigh, NC, Jun 29-Jul 2, 2016).
Quelle	(2016), (8 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	Word Problems (Mathematics); Mathematics Instruction; Arithmetic; Problem Solving; Models; Classification; Elementary School Students; Student Behavior; Behavior Patterns; Computer Uses in Education; Prediction; Automation; Sequential Learning; Foreign Countries; Grade 2; Data Analysis; Persistence; Singapore + Suchen Sie Ihr Suchwort? Textaufgabe; Mathematics lessons; Mathematikunterricht; Addition; Arithmetik; Arithmetikunterricht; Rechnen; Problemlösen; Analogiemodell; Classification system; Klassifikation; Klassifikationssystem; Student behaviour; Schülerverhalten; Computernutzung; Vorhersage; Didaktische Sequenzierung; Lernsequenz; Ausland; School year 02; 2. Schuljahr; Schuljahr 02; Auswertung; Ausdauer; Singapur
Abstract	During the semester break, 36 second-grade students accessed a set of resources and completed a series of online math activities focused on the application of the model method for arithmetic in two contexts 1) addition/subtraction and 2) multiplication/division. The learning environment first modeled and then supported the use of a scripted series of steps for solving mathematical word problems. As students completed the activities, the learning environment captured their event-related data. We then used a combination of Affinity Propagation, an automated form of clustering, and sequential pattern mining to convert the activity logs into interpretable activity sequences. Analysis of the activity sequences identified distinct patterns of behavior that strongly predicted which students would transit from the familiar addition/subtraction word problem activity to the unfamiliar multiplication/division word problem activity. Students who showed the greatest and least compliance with the script were the least likely to attempt the multiplication/division activity. Students who showed more of a schematic problem solving process were more likely to continue to the multiplication/division activity. (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