What Decides the Dropout in MOOCs?

Lu, Xiaohang; Wang, Shengqing; Huang, Junjie; Chen, Wenguang; Yan, Zengwang

doi:10.1007/978-3-319-55705-2_25

Cited by 21 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…MOOCs originated with the Connectivism and Connective Knowledge MOOC provided by University of Manitoba in 2008 [19], but the introduction of Coursera, edX and Udacity MOOC platforms in 2012 led a significant trend [29]. There are two types of MOOCs, distinguished by their pedagogy.…”

Section: Background To Moocsmentioning

confidence: 99%

“…Researchers found lack of time, lack of engagement. Interactions as key reasons [2,24] for attrition and many of studies provide predictive modeling techniques to identify drop outs [18,31,39]. Other studies found that bad time managements skill of students lead to drop outs and suggested that platforms should not only provide their users with high quality educational materials with interaction but platforms should design to support uplift skills of the user [25].…”

Section: Evaluating Moocsmentioning

confidence: 99%

See 1 more Smart Citation

MOOCs Lack Interactivity and Collaborativeness: Evaluating MOOC Platforms

2020

View full text Add to dashboard Cite

Massive open online courses (MOOCs) have considered to be a potential to disseminate engineering education at scale. However, the pedagogical requirement demanded engineering student to equip with specific skillsets such as communication, interactivity, and collaboration. Yet, MOOCs are skeptical of facilitating those skills. Generally, MOOCs evaluated against accessibility and usability. These evaluations may not perceive whether the platform designs in MOOCs support to much-needed interactions and collaboration required in engineering education. We evaluated 6 MOOC platform designs under the lens of collaboration and types of interactions which occur as learner to learner, learner to instructor, learner to platform and learner to content. Evaluation criteria were derived us-ing previous frameworks and evaluations were conducted using 10 participants. Based on each criterion a matrix was formed with a weight to compare results. We found overall collaboration opportunities in platforms are significantly less than the opportunities to interact. Based on the findings we provide 5 design recommendations and provide a future direction for MOOC platform designs which en-ables facilitation to engineering education through MOOCs.

show abstract

Section: Background To Moocsmentioning

confidence: 99%

Section: Evaluating Moocsmentioning

confidence: 99%

MOOCs Lack Interactivity and Collaborativeness: Evaluating MOOC Platforms

2020

View full text Add to dashboard Cite

show abstract

“…Several works based on statistics, Machine Learning (ML) and visualisation have focused on analyses and predictions of MOOC learner behaviour. (Lu et al 2017) extracted a large number of features (19) to predict dropout, based on ML methods and support vector machines (SVM), from five courses (one run each only) on Coursera. (Robinson et al 2016) used NLP techniques to predict dropout on only one HarvardX course; language features were selected via the lasso logistic regression model, and performance was evaluated with Area Under Curve (AUC).…”

Section: Behaviour-based Predictionmentioning

confidence: 99%

Towards Designing Profitable Courses: Predicting Student Purchasing Behaviour in MOOCs

Alshehri

Alamri

Cristea

et al. 2021

Int J Artif Intell Educ

View full text Add to dashboard Cite

Since their ‘official’ emergence in 2012 (Gardner and Brooks 2018), massive open online courses (MOOCs) have been growing rapidly. They offer low-cost education for both students and content providers; however, currently there is a very low level of course purchasing (less than 1% of the total number of enrolled students on a given online course opt to purchase its certificate). The most recent literature on MOOCs focuses on identifying factors that contribute to student success, completion level and engagement. One of the MOOC platforms’ ultimate targets is to become self-sustaining, enabling partners to create revenues and offset operating costs. Nevertheless, analysing learners’ purchasing behaviour on MOOCs remains limited. Thus, this study aims to predict students purchasing behaviour and therefore a MOOCs revenue, based on the rich array of activity clickstream and demographic data from learners. Specifically, we compare how several machine learning algorithms, namely RandomForest, GradientBoosting, AdaBoost and XGBoost can predict course purchasability using a large-scale data collection of 23 runs spread over 5 courses delivered by The University of Warwick between 2013 and 2017 via FutureLearn. We further identify the common representative predictive attributes that influence a learner’s certificate purchasing decisions. Our proposed model achieved promising accuracies, between 0.82 and 0.91, using only the time spent on each step. We further reached higher accuracy of 0.83 to 0.95, adding learner demographics (e.g. gender, age group, level of education, and country) which showed a considerable impact on the model’s performance. The outcomes of this study are expected to help design future courses and predict the profitability of future runs; it may also help determine what personalisation features could be provided to increase MOOC revenue.

show abstract

“…Nesse cenário, a Mineração de Dados Educacionais (MDE), uma área de pesquisa interdisciplinar que lida com o desenvolvimento de métodos para explorar dados originados no âmbito educacional (Romero & Ventura, 2016) tem ganhado destaque. As técnicas de MDE almejam a extração de informações dos dados registrados pelas plataformas no decorrer da realização de um MOOC, e que podem conduzir à identificação de características comportamentais e indicadores relacionados à aprendizagem (Lu et al, 2017). Baker, Isotani & Carvalho (2011) afirmam que as principais contribuições da MDE são: (1) a criação de modelos para melhor compreender os processos de aprendizagem; e (2) o desenvolvimento de métodos mais eficazes para dar suporte à aprendizagem quando o aluno estuda utilizando softwares educacionais ou Ambiente Virtuais de Ensino Aprendizagem (AVAs).…”

Section: Introductionunclassified

Tendências de Pesquisas em Mineração de Dados Educacionais em MOOCs: um Mapeamento Sistemático

Souza

Perry

2020

RBIE

View full text Add to dashboard Cite

ResumoMassive Open Online Courses (MOOCs) são uma modalidade de curso que utilizam plataformas online e atraem diferentes perfis de estudantes, ofertando oportunidades de qualificação - seja formal ou informal - em um formato bastante dinâmico. Uma característica das plataformas que ofertam tais cursos é a capacidade de armazenar uma grande quantidade de dados, o que possibilitou a exploração destes dados por meio de técnicas de Mineração de Dados Educacionais (MDE). Nesse contexto, foi conduzido um mapeamento sistemático de literatura em cinco bases de dados com o propósito de verificar quais as vertentes de estudos em destaque quanto ao uso de MDE em MOOCs. A busca compreendeu o período de 2015 a 2020, sendo que 158 foram selecionados. Os resultados revelaram que estudos relativos à Análise de Comportamento, Predição (de Desempenho, de Abandono, de Conclusão), Mineração de Texto e Sistemas de Recomendação são os mais frequentes. Além disso, foram identificadas áreas com potencial de exploração, como Social Network Analysis (SNA), Digital Learning Ecosystem (DLE) e Análise de Mind Wandering (MW). Ademais, foram levantados métodos e ferramentas usados nas pesquisas, bem como desafios do uso de MDE na pesquisa sobre MOOC. Conclui-se que a questão do desequilíbrio de classes, provocado pela baixa adesão aos cursos, é um dos maiores desafios.Palavras-Chave: MOOCs, Mineração de Dados Educacionais, Mapeamento Sistemático. AbstractMassive Open Online Courses (MOOCs) use online platforms and attract different student profiles, offering qualification opportunities - whether formal or informal - in a very dynamic format. A characteristic of the platforms that offer such courses is the ability to store a large amount of data, which made it possible to explore it through Educational Data Mining (EDM) techniques. In this context, a systematic scoping was conducted in five databases with the purpose of discover research trends regarding to the use of EDM in MOOCs. The search covered the period from 2015 to 2020, selecting 158 papers. The results revealed that studies related to Behavior Analysis, Prediction (Performance, Abandonment, Conclusion), Text Mining and Recommendation Systems are the most frequent. Promissing researches were also identified, such as Social Network Analysis (SNA), Digital Learning Ecosystem (DLE) and Mind Wandering Analysis (MW). Methods and tools used in research were listed, as well as challenges in the use of EDM in research on MOOC. We concluded that the issue of class imbalance, caused by low adherence to courses, is one of the biggest challenges.Keywords: MOOCs, Educational Data Mining, Systematic Scoping.

show abstract

What Decides the Dropout in MOOCs?

Cited by 21 publications

References 8 publications

MOOCs Lack Interactivity and Collaborativeness: Evaluating MOOC Platforms

MOOCs Lack Interactivity and Collaborativeness: Evaluating MOOC Platforms

Towards Designing Profitable Courses: Predicting Student Purchasing Behaviour in MOOCs

Tendências de Pesquisas em Mineração de Dados Educacionais em MOOCs: um Mapeamento Sistemático

Contact Info

Product

Resources

About