Predicting Student Examinee Rate in Massive Open Online Courses

Lu, Wei; Wang, Tongtong; Jiao, Min; Zhang, Xiaoying; Wang, Shan; Du, Xiaoyong; Hong, Chen

doi:10.1007/978-3-319-55705-2_27

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a Bayesian classifier (based on the application of the Bayes' theorem), which assigns samples with the most likely class according to the features, assuming that features are independent given the class [103]. As an example, Lu et al [104] used several predictive models, including Naive Bayes, to forecast whether a learner was going to take the final exam of the MOOC or not. The study used three courses and the best model differed for each case, although Naive Bayes achieved the best recall in one of them.…”

Section: Distribution Of Prediction Features In Moocsmentioning

confidence: 99%

Prediction in MOOCs: A Review and Future Research Directions

Moreno-Marcos

Alario-Hoyos

Muñoz‐Merino

et al. 2019

IEEE Trans. Learning Technol.

130

View full text Add to dashboard Cite

This paper surveys the state of the art on prediction in MOOCs through a Systematic Literature Review (SLR). The main objectives are: (1) to identify the characteristics of the MOOCs used for prediction, (2) to describe the prediction outcomes, (3) to classify the prediction features, (4) to determine the techniques used to predict the variables, and (5) to identify the metrics used to evaluate the predictive models. Results show there is strong interest in predicting drop-outs in MOOCs. A variety of predictive models are used, though regression and Support Vector Machines stand out. There is also wide variety in the choice of prediction features, but clickstream data about platform use stands out. Future research should focus on developing and applying predictive models that can be used in more heterogeneous contexts (in terms of platforms, thematic areas, and course durations), on predicting new outcomes and making connections among them (e.g., predicting learners' expectancies), on enhancing the predictive power of current models by improving algorithms or adding novel higher-order features (e.g., efficiency, constancy, etc.).

show abstract

Section: Distribution Of Prediction Features In Moocsmentioning

confidence: 99%