Finding out Reasons for Low Completion in MOOC Environment: An Explicable Approach Using Hybrid Data Mining Methods

Abstract

Abstract. Because of the worldwide rapid development of MOOC, academic researches and industrial applications of MOOC have become a branch of the major concerns in modern education and information technology fields. This paper focuses on low completion phenomenon in MOOC environment and proposes an explicable approach to find out hidden reasons convincingly. Different from existing works, this approach utilizes data mining methods to make quantitative analysis. It employs learners clustering basing on their study features at first, aiming at discovering inactive learners automatically. These learners are representative of low completion in course study on MOOC platform. Their study behaviors and interactions with website are analyzed with association rules mining in order to explore potential patterns and rules. The extracted rules are used to find out and explain the reasons for low completion in MOOC environment. The experimental result on practical XuetangX platform reveals several strong rules with high support, confidence and lift, which can be regarded as evidence and reference for further explanations of reasons for low completion in MOOC environment.

MOOC dropout prediction using machine learning techniques: Review and research challenges

“…Different from other works, [19] apply an approach that used K-means to make quantitative analysis by employing students clustering aiming at discovering inactive students automatically in MOOC environment. Qiu et al [20] among other researchers focus on proposing dropout prediction models based on support vector machines.…”

MOOC: Pensamiento Computacional (aplicado) para docentes

“…Los resultados son superiores a los tradicionales de MOOCs. Si bien no hay consenso en el valor de compleción general de MOOCs, en general dicho valor es bajo [36]. Por ejemplo, es 5% para Button [13], según [10] la tasa de compleción de MOOCs es menor al 10% y para Onah et al [37] el valor promedio es 13%.…”

On the Effectiveness of Self-Training in MOOC Dropout Prediction

“…Moreno-Marcos et al [53] 2020 Coursera MOOC RF, GLM, SVM & DT Xing and Du [54] 2019 Canvas MOOC DL Liu and Li [55] 2017 XuetangX MOOC K-means Nagrecha et al [31] 2017 edX MOOC DT & LR Chen and Zang [56] 2017 Coursera MOOC RF Xing et al [43] 2016 Canvas MOOC GBN & DT Crossley et al [48] 2016 Coursera MOOC NLP Chaplot et al [46] 2015 [42] for successful predictions. Among ML algorithms, some works also focus on decision tree [43][44][45], sentiment-based artificial neural network [46], deep neural network [47], and natural language processing statistical models [48][49][50].…”