Analyzing Early At-Risk Factors in Higher Education E-Learning Courses [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (8th, Madrid, Spain, Jun 26-29, 2015).

Autor/inn/en	Baker, Ryan S.; Lindrum, David; Lindrum, Mary Jane; Perkowski, David
Institution	International Educational Data Mining Society
Titel	Analyzing Early At-Risk Factors in Higher Education E-Learning Courses [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (8th, Madrid, Spain, Jun 26-29, 2015).
Quelle	(2015), (6 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
Schlagwörter	College Students; At Risk Students; Online Courses; Educational Technology; Technology Uses in Education; College Faculty; Predictor Variables; Formative Evaluation; History Instruction; Web Based Instruction; Grades (Scholastic); Academic Achievement; Assignments; Regression (Statistics); Success + Suchen Sie Ihr Suchwort? Collegestudent; Online course; Online-Kurs; Unterrichtsmedien; Technology enhanced learning; Technology aided learning; Technologieunterstütztes Lernen; Fakultät; Prädiktor; History lessons; Geschichtsunterricht; Web Based Training; Notenspiegel; Schulleistung; Assignment; Auftrag; Zuweisung; Regression; Regressionsanalyse; Erfolg
Abstract	College students enrolled in online courses lack many of the supports available to students in traditional face-to-face classes on a campus such as meeting the instructor, having a set class time, discussing topics in-person during class, meeting peers and having the option to speak with them outside of class, being able to visit faculty during office hours, and so on. Instructors also lack these interactions, which typically provide meaningful indications of how students are doing individually and as a cohort. Further, online instructors typically carry a heavier teaching load, making it even more important for them to find quick, reliable, and easily understandable indicators of student progress, so that they can prioritize their interventions based on which students are most in need. In this paper, we study very early predictors of student success and failure. Our data is based on student activity, and is drawn from courses offered online by a large private university. Our data source is the Soomo Learning Environment, which hosts the course content as well as extensive formative assessment. We find that students who access the resources early, continue accessing the resources throughout the early weeks of the course, and perform well on formative activities are more likely to succeed. Through use of these indicators in early weeks, it is possible to derive actionable, understandable, and reasonably reliable predictions of student success and failure. [For complete proceedings, see ED560503.] (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