Analyzing MOOC Forums: Developing Models to Support Instructors' Monitoring of Learners' Posts

Literaturnachweis - Detailanzeige

Trefferliste

Autor/in	Almatrafi, Omaima
Titel	Analyzing MOOC Forums: Developing Models to Support Instructors' Monitoring of Learners' Posts
Quelle	(2018), (139 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, George Mason University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-0-4388-8911-8
Schlagwörter	Hochschulschrift; Dissertation; Large Group Instruction; Online Courses; Educational Technology; Technology Uses in Education; Computer Mediated Communication; Group Discussion; Interaction; Data Collection; Data Analysis; Teacher Role; Student Attitudes; Models; Electronic Publishing; Teaching Methods + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Online course; Online-Kurs; Unterrichtsmedien; Technology enhanced learning; Technology aided learning; Technologieunterstütztes Lernen; Computerkonferenz; Gruppendiskussion; Interaktion; Data capture; Datensammlung; Auswertung; Lehrerrolle; Schülerverhalten; Analogiemodell; Elektronisches Publizieren; Teaching method; Lehrmethode; Unterrichtsmethode
Abstract	A Massive Open Online Course (MOOC) is a course that is offered fully online and is usually open for enrollment by any individual, with no limit on the number of participants. MOOCs are a popular resource for learning worldwide with over 23 million new learners registering for MOOCs in 2017 alone. Coursera, the most popular MOOC platform, has registered over 30 million learners since its founding in 2012. In online courses, discussion forums are a vital component since this is where learners interact with other learners and the instructor(s), build a sense of community, and generate knowledge. Within MOOCs, discussion forums are the primary channel for social learning and interaction. Given the extremely large number of learners, the use of discussion forums becomes chaotic shortly after the course begins. This dissertation addresses this problem and the overarching research question of this work is--with a limited number of instructors, how can learning analytics help instructors monitor and manage discussion forums in MOOCs? To address this question, a three part study was undertaken. In the first part a systematic review of peer-reviewed articles was conducted to identify areas for contribution where instructors can be assisted through automated analysis of MOOC forums. Two primary goals were identified and subsequently this dissertation focused on a) classification of posts that need urgent attention from instructors; and, b) monitoring of learners' attitudes towards aspects of the course and learners' suggestions for course improvement. MOOCPosts dataset, which contains about 30,000 posts collected from eleven courses, was used to build and evaluate the models. The first study developed a model that can identify posts that require instructors' attention in MOOC discussion forums regardless of the course the post belongs to. Different features-extraction and model-building methods were tested. The best method was then used to evaluate the constructed model on unseen courses. The findings highlighted linguistic features of urgent posts and the best performing method. In the second study, the objective was to develop a model that summarizes learners' opinions regarding course aspects and extract suggestions for course improvement from MOOC discussion forums. Syntactical rules and lexicons were used for posts classification, and visualization for summarization. Both studies achieved the desired goals with moderate to substantial reliability using Cohen's Kappa. The contribution of this research aims to help instructors make informed decisions related to teaching pedagogy adjustment and individual support intervention. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01