A Sequence Data Model for Analyzing Temporal Patterns of Student Data

Autor/inn/en	Mahzoon, Mohammad Javad; Maher, Mary Lou; Eltayeby, Omar; Dou, Wenwen; Grace, Kazjon
Titel	A Sequence Data Model for Analyzing Temporal Patterns of Student Data
Quelle	In: Journal of Learning Analytics, 5 (2018) 1, S.55-74 (20 Seiten)Infoseite zur Zeitschrift PDF als Volltext kostenfreie Datei Verfügbarkeit
Zusatzinformation	ORCID (Mahzoon, Mohammad Javad)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1929-7750
Schlagwörter	Data Analysis; Learning; Models; Time; Student Experience; College Students; Computer Science Education; Introductory Courses; Prediction; At Risk Students; North Carolina (Charlotte) + Suchen Sie Ihr Suchwort? Auswertung; Lernen; Analogiemodell; Zeit; Studienerfahrung; Collegestudent; Computer science lessons; Informatikunterricht; Einführungskurs; Vorhersage
Abstract	Data models built for analyzing student data often obfuscate temporal relationships for reasons of simplicity, or to aid in generalization. We present a model based on temporal relationships of heterogeneous data as the basis for building predictive models. We show how within- and between-semester temporal patterns can provide insight into the student experience. For example, in a within-semester model, the prediction of the final course grade can be based on weekly activities and submissions recorded in the LMS [learning management system]. In the between-semester model, the prediction of success or failure in a degree program can be based on sequence patterns of grades and activities across multiple semesters. The benefits of our sequence data model include temporal structure, segmentation, contextualization, and storytelling. To demonstrate these benefits, we have collected and analyzed 10 years of student data from the College of Computing at UNC [University of North Carolina] Charlotte in a between-semester sequence model, and used data in an introductory course in computer science to build a within-semester sequence model. Our results for the two sequence models show that analytics based on the sequence data model can achieve higher predictive accuracy than non-temporal models with the same data. (As Provided).
Anmerkungen	Society for Learning Analytics Research. 121 Pointe Marsan, Beaumont, AB T4X 0A2, Canada. Tel: +61-429-920-838; e-mail: info@solaresearch.org; Web site: http://learning-analytics.info/journals/index.php/JLA/
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01