Detecting the Depth and Progression of Learning in Massive Open Online Courses by Mining Discussion Data
- PDF / 1,897,118 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 65 Downloads / 188 Views
Detecting the Depth and Progression of Learning in Massive Open Online Courses by Mining Discussion Data Venkata Sai Pillutla1 · Andrew A. Tawfik2 · Philippe J. Giabbanelli3
© Springer Nature B.V. 2020
Abstract In massive open online courses (MOOCs), learners can interact with each other using dis‑ cussion boards. Automatically inferring the states or needs of learners from their posts is of interest to instructors, who are faced with a high attrition in MOOCs. Machine learning has previously been successfully used to identify states such as confusion or posting ques‑ tions, but no solution has yet been provided so that instructors can track the progress of the learners using a validated framework from education research. In this paper, we develop a model to automatically label a post based on the first phase of the interaction analysis model (IAM). This allows instructors to automatically identify whether students are stating opinions, clarifying details, or engaging in activities such as providing examples to peers. Our model is tested on a Coursera MOOC devoted to Chemistry, for which we are able to correctly categorize the IAM status in 4 out of 5 posts. Our approach thus provides instruc‑ tors with an intelligent system that generates actionable learning assessment data and can cope with large enrollment. Using the system, instructors can quickly identify and remedy learning issues, thus supporting learners in attaining their intended outcomes. Keywords Computer supported collaborative learning · Learning analytics · Massive open online courses · Supervised learning · Text mining
* Philippe J. Giabbanelli [email protected] Venkata Sai Pillutla [email protected] Andrew A. Tawfik [email protected] 1
Loven Systems, 22260 Haggerty Rd, Northville, MI 48167, USA
2
Department of Instructional Design and Technology, University of Memphis, 406 E.C. Ball Hall, Memphis, TN 37152‑3570, USA
3
Department of Computer Science and Software Engineering, Miami University, 205 Benton Hall, 510 E High St, Oxford, OH 45056, USA
13
Vol.:(0123456789)
V. S. Pillutla et al.
1 Introduction Addressing systemic barriers that prevent access to education is an important issue in higher education (Darling-Hammond 2013). Traditionally, learners needed to find means of transportation to attend established ‘brick and mortar’ universities. Online learning pro‑ vided an alternative since space and time constraints were less of an impediment to edu‑ cational opportunities (Reeves and Bonk 2015; Tawfik et al. 2017). More recently, mas‑ sive open online courses (MOOCs) provide an additional avenue for learners to access knowledge from established, reputable universities (Shapiro et al. 2017). Whereas access to online learning was still influenced by admission requirements (Amemado and Manco 2017; Chapman et al. 2016), MOOCs allow learners to take classes with little or no enrol‑ ment criteria (Kizilcec et al. 2017; Hood et al. 2015). Learners can thus take MOOCs classes as-needed from different providers and forma
Data Loading...
