A systematic review for MOOC dropout prediction from the perspective of machine learning

Jing, Chen; Fang, Bei; Zhang, Hao; Xue, Xiaomin

doi:10.1080/10494820.2022.2124425

Cited by 10 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These research reviews synthesize published studies from the previous decade (2010–2020), and thus provide a great scope of the research field. Still, we find that drop-out, retention, and attrition issues spark great research interest (Chen et al, 2022 ; Chiappe & Castillo, 2021 ; Estrada-Molina & Fuentes-Cancell, 2022 ; Wang et al, 2022 ). These research reviews are prone to emphasizing different explanations as to why learners drop out of MOOCs, which can be attributed to ineffective online course design, lack of belonging, time factors, and hidden costs, etc.…”

Section: Theoretical Perspectivesmentioning

confidence: 92%

Institutional Entrepreneurship in Loosely Coupled Systems: The Subject Position of MOOC Entrepreneurs and Their Interpretive Struggles in a Norwegian Context

2023

View full text Add to dashboard Cite

While technological change in organizations is fast and eminent to most people, the adoption of Massive Open Online Courses, micro-credentials, and flexible and scalable online courses, appear to be comparatively slow in Higher Education in the Nordic countries. To explore this phenomenon, we completed 10 qualitative interviews at ten different higher education institutions across Norway in fall 2020. The informants were strategically selected among employees who had been involved in open platform technology, MOOC production and support for faculties. Adopting thematic analyses, we found entrepreneurs who positioned themselves in pockets of innovation with the intention to transform teaching and learning. Rather than seeing technological innovations as “more of the same”, the entrepreneurs embraced the possibilities emerging in new educational practices. Inspired by New Institutionalism, we focused on the organizational conditions for MOOC production. The entrepreneurs often entered interpretive struggles at higher organizational levels in competition with other stakeholders. Despite national initiatives and funding, many stakeholders questioned the value of MOOCs. Our study points to discrepancies in understanding the disruptive and transformative change that new technology can bring to study programs and lifelong learning. The informants also experienced insufficient support from leaders and lamented the lack of a national platform for open online access. We link these findings to embedded theories, belief systems and discourses in educational cultures and management in Higher Education.

show abstract

Section: Theoretical Perspectivesmentioning

confidence: 92%

Institutional Entrepreneurship in Loosely Coupled Systems: The Subject Position of MOOC Entrepreneurs and Their Interpretive Struggles in a Norwegian Context

2023

View full text Add to dashboard Cite

show abstract

“…In [6], another extension of BPR (EBPR) is proposed where users' consumption behavior such as reading a news article or listening to a music track is used to model users' preferences. Dropout prediction in MOOCs has been extensively studied as a classification problem, and several Machine Learning models were used [2,4]. However, in such examples, time information was mostly discarded.…”

Section: Related Workmentioning

confidence: 99%

“…We evaluated our approach by using three widely used publicly available datasets, namely XuetangX [5], KDDCUP [5], and Canvas [14]. Both KDD-CUP and Xuetangx anonymized datasets are provided by XuetangX 2 The hyperparameter tuning procedure is explained in Section 4. 2 describes the three (preprocessed) publicly available datasets relating to MOOCs that were used to evaluate the proposed approach.…”

Section: Experimental Design 41 Datasets Prepossessing and Descriptionmentioning

confidence: 99%

“…Despite the growing popularity of Massive Open Online Courses (MOOCs), both in contexts of independent (self-directed) learning and in formal educational programs, learning in MOOCs is characterized by a very high dropout rate. Average dropout rates of up to 90% have been reported in courses offered by premier institutions like MIT and Harvard [2]. Tackling the challenge of dropout in MOOCs requires both an empirical understanding of the phenomenon, informed by theory in the learning sciences (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extending Bayesian Personalized Ranking with Survival Analysis for MOOC Recommendation

Gharahighehi,

Venturini,

Ghinis

et al. 2023

Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

Massive Open Online Courses (MOOCs) have recently attracted students and professionals as complementary tools to academic education. Despite the number of advantages MOOCs provide, such as openness and flexibility regarding learning pace, such courses are characterized by a consistently higher dropout rate than conventional classrooms. A crucial factor that influences dropout is the choice of the appropriate course, hence the need for effective course recommendations. A course recommendation system (RS) that uses dropout information can mitigate course withdrawal and user dissatisfaction. In this paper, an extension of Bayesian Personalized Ranking, which is a learning-to-rank RS, is proposed that uses the pseudo-labels extracted by survival analysis based on dropout information to recommend courses in the context of MOOCs. The proposed approach performs the best compared to six competing RSs on three MOOCs datasets. CCS CONCEPTS• Information systems → Recommender systems; Collaborative filtering; • Mathematics of computing → Survival analysis.

show abstract

Structuring Continuous Education Offers for E-Government-Competence Acquisition: A Morphological Box

Koelmann,

Koddebusch,

Bücker

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A systematic review for MOOC dropout prediction from the perspective of machine learning

Cited by 10 publications

References 45 publications

Institutional Entrepreneurship in Loosely Coupled Systems: The Subject Position of MOOC Entrepreneurs and Their Interpretive Struggles in a Norwegian Context

Institutional Entrepreneurship in Loosely Coupled Systems: The Subject Position of MOOC Entrepreneurs and Their Interpretive Struggles in a Norwegian Context

Extending Bayesian Personalized Ranking with Survival Analysis for MOOC Recommendation

Structuring Continuous Education Offers for E-Government-Competence Acquisition: A Morphological Box

Contact Info

Product

Resources

About