MOOC Dropout Research Articles

Early prediction of MOOC dropout in self-paced students using deep learning

ABSTRACT To address three issues identified in previous research this study proposes a clustering-based MOOC dropout identification method and an early prediction model based on deep learning. The MOOC learning behavior of self-paced students was analyzed, and two well-known MOOC datasets were used for analysis and validation. The findings are as follows: Firstly, the dropout rate among self-paced students in MOOCs exceeds 90%, with over 50% of students participating in online learning activities for only one day. Furthermore, the starting dates for students in the same course differ significantly. Secondly, leveraging early learning behavior and relevant background features, the proposed early prediction model accurately predicts over 98% of dropout cases and identifies over 50% of engaged students. Through training, the model's convolutional kernels capture meaningful weights for different days and activities. Lastly, background features related to students and courses have a more significant impact on dropout rates. The utilization of resources such as videos and active participation in learning activities, like asking questions, demonstrate a particularly significant influence on dropout rates. Notably, there is no fixed period that consistently affects dropout rates. These method and findings provide effective strategies for decreasing dropout rates and improving student engagement.

Dropout Prediction Model for College Students in MOOCs Based on Weighted Multi-feature and SVM

Due to the COVID -19 pandemic, MOOCs have become a popular form of learning for college students. However, unlike traditional face-to-face courses, MOOCs offer little faculty supervision, which may result in students being insufficiently motivated to continue learning, ultimately leading to a high dropout rate. Consequently, the problem of high dropout rates in MOOCs requires urgent attention in MOOC research. Predicting dropout rates is the first step to address this problem, and MOOCs have a large amount of behavioral data that can be used for such predictions. Most existing models for predicting MOOC dropout based on behavioral data assign equal weights to each behavioral characteristic, despite the fact that each behavioral characteristic has a different effect on predicting dropout. To address this problem, this paper proposes a dropout prediction model based on the fusion of behavioral data and Support Vector Machine (SVM). This innovative model assigns different weights to different behavior features based on Pearson principle and integrates them as data inputs to the model. Dropout prediction is essentially a binary problem, Support Vector Machine Classifier is then trained using the training dataset 1 and dataset 2. Experimental results on both datasets show that this predictive model outperforms previous models that assign the same weights to the behavior features.

Learning behavior feature fused deep learning network model for MOOC dropout prediction

Learning behavior feature fused deep learning network model for MOOC dropout prediction

An Explainable Machine Learning Approach to Predicting and Understanding Dropouts in MOOCs

Purpose: The purpose of this study is to predict dropouts in two runs of the same MOOC using an explainable machine learning approach. With the explainable approach, we aim to enable the interpretation of the black-box predictive models from a pedagogical perspective and to produce actionable insights for related educational interventions. The similarity and the differences in feature importance between the predictive models were also examined.
 Design/Methodology/Approach: This is a quantitative study performed on a large public dataset containing activity logs in a MOOC. In total, 21 features were generated and standardized before the analysis. Multi-layer perceptron neural network was used as the black-box machine learning algorithm to build the predictive models. The model performances were evaluated using the accuracy and AUC metrics. SHAP was used to obtain explainable results about the effects of different features on students’ success or failure.
 Findings: According to the results, the predictive models were quite accurate, showing the capacity of the features generated in capturing student engagement. With the SHAP approach, reasons for dropouts for the whole class, as well as for specific students were identified. While mostly disengagement in assignments and course wares caused dropouts in both course runs, interaction with video (the main teaching component) showed a limited predictive power. In total six features were common strong predictors in both runs, and the remaining four features belonged to only one run. Moreover, using waterfall plots, the reasons for predictions pertaining to two randomly chosen students were explored. The results showed that dropouts might be explained by different predictions for each student, and the variables associated with dropouts might be different than the predictions conducted for the whole course.
 Highlights: This study illustrated the use of an explainable machine learning approach called SHAP to interpret the underlying reasons for dropout predictions. Such explainable approaches offer a promising direction for creating timely class-wide interventions as well as for providing personalized support for tailored to specific students. Moreover, this study provides strong evidence that transferring predictive models between different contexts is less like to be successful.

A Time-Aware Approach for MOOC Dropout Prediction Based on Rule Induction and Sequential Three-Way Decisions

A Time-Aware Approach for MOOC Dropout Prediction Based on Rule Induction and Sequential Three-Way Decisions

Factors of dropout from MOOCs: a bibliometric review

PurposeAlthough MOOCs have become a pervasive online learning model, the problem of high dropout rates still persists. Gathering the reasons for the high dropout rate can help to improve the platform design and management of the MOOCs.Design/methodology/approachA total of 74 studies was extracted from the Web of Science and Scopus. Following the PRISMA (Preferred Reporting Items for systematic Reviews and Meta-Analyses) guidelines, the open-source program CiteSpace is employed to review and induce the studies on the antecedents of MOOC dropout.FindingsThe antecedents of the MOOC dropout rate are the psychological, social, personal, course-related, and time factors, and the unexpected hidden cost. Motivation and interaction, which have a decisive impact on the dropout rate of MOOCs, interact with each other. Interaction helps to strengthen the motivation, and appropriate course design enhances the degree of interaction.Originality/valueFrom the perspective of a learner, the more knowledge and skills the learners acquire, the more likely they will complete the course. Possessing adequate foundational knowledge is one way to arrest the dropout rate. On the part of the MOOC platform, better course design eases the dropout rate. Further, the course duration and hidden cost in MOOCs contribute to the dropout rate.

How do online learning intentions lead to learning outcomes? The mediating effect of the autotelic dimension of flow in a MOOC

We focus on the predictors of persistence and achievement in online learning by studying the students’ learning intentions and their psychological states during learning activities. Flow/autotelic experience is a powerful predictor of engagement in MOOCs and online learning in general and relates to the deep involvement and sense of absorption during learning activities. Both theory and empirical evidence propose that predictors of flow in an educational setting include the need for belonging to a group of learners. Using path analyses and structural equation modeling, we verify the causal links between social intentions, autotelic experience and MOOC learning outcomes such as final grade and dropout. Using the Online Learning Enrollment Intentions (OLEI) scale, we find that in total six OLEI items predict MOOC success and dropout, with flow as a mediating effect. In two models, we verify “Autotelic experience” as a mediator between enrollment intentions and MOOC final grade and dropout. Our results highlight socially driven intentions as major factors to be considered in online learning environments. We draw theoretical and practical implications for MOOC design, considering explicit communication about the provided learning environment and tools towards a socially shared learning experience.

The role of motivation in MOOCs\u2019 retention rates: a systematic literature review

Although MOOCs platforms offer a unique way to provide information for a large cohort of participants, only a small percentage of participants complete MOOCs. The high number of dropouts in MOOCs is a key challenge, and the literature suggests that it can be affected by participants' motivation. However, it is not known how and to what extent motivation influences participants’ dropout in MOOCs. There is a need to provide an overview of the role of motivation in MOOCs’ retention. In this study, we aimed to identify motivational factors and theories that affect participants’ retention in MOOCs and explain how does motivation supports participants to complete MOOCs. To do so, a systematic review was conducted using specific inclusion and exclusion criteria and a set of relevant keywords and databases which resulted in 50 relevant publications. Our analysis led us to identify six main motivational factors that influence participants’ MOOCs completion including academic, social, course, personal, professional, and technological motives. These factors were divided into two main categories including need-based motivation and interest-based motivation. The results showed that academic motives play the most important role in participants’ MOOCs retention compared to the other factors. It was also found that self-determination theory was used as the most dominant theory to support participants’ motivation for MOOCs completion. In addition, the results revealed that the motivational factors not only impacts participants’ MOOCs retention directly, but also this impact is mediated by participant satisfaction, self-regulation, attitude toward using MOOCs, performance, engagement, and level of participation. Based on the results, further implications for practice and future research are provided.

CLSA: A novel deep learning model for MOOC dropout prediction

MOOCs have attracted hundreds of millions of learners with advantages such as being cost-free and having flexible time and space. However, high dropout rates have become the main issue that hinders their further progress. To solve this problem, this research proposes a pipeline model named CLSA to predict the dropout rate based on learners’ behavior data. The CLSA model first uses a convolutional neural network to extract local features and builds feature relations using a kernel strategy. Then, it feeds this high-dimensional vector generated by the CNN to a long short-term memory network to obtain a time-series incorporated vector representation. After that, it employs a static attention mechanism on the vector to obtain an attention weight on each dimension. When tested on the KDD CUP 2015 dataset, our model reached 87.6% accuracy, which was higher than the previous best model (over 2.8%). The F1-score of our model reached 86.9%, which was 1.6% higher than the previous state-of-the-art result.

On the Effectiveness of Self-Training in MOOC Dropout Prediction

AbstractMassive open online courses (MOOCs) have gained enormous popularity in recent years and have attracted learners worldwide. However, MOOCs face a crucial challenge in the high dropout rate, which varies between 91%-93%. An interplay between different learning analytics strategies and MOOCs have emerged as a research area to reduce dropout rate. Most existing studies use click-stream features as engagement patterns to predict at-risk students. However, this study uses a combination of click-stream features and the influence of the learner’s friends based on their demographics to identify potential dropouts. Existing predictive models are based on supervised learning techniques that require the bulk of hand-labelled data to train models. In practice, however, scarcity of massive labelled data makes training difficult. Therefore, this study uses self-training, a semi-supervised learning model, to develop predictive models. Experimental results on a public data set demonstrate that semi-supervised models attain comparable results to state-ofthe-art approaches, while also having the flexibility of utilizing a small quantity of labelled data. This study deploys seven well-known optimizers to train the self-training classifiers, out of which, Stochastic Gradient Descent (SGD) outperformed others with the value of F1 score at 94.29%, affirming the relevance of this exposition.

Internationalizing Professional Development: Using Educational Data Mining to Analyze Learners’ Performance and Dropouts in a French MOOC

This paper uses data mining from a French project management MOOC to study learners’ performance (i.e., grades and persistence) based on a series of variables: age, educational background, socio-professional status, geographical area, gender, self- versus mandatory-enrollment, and learning intentions. Unlike most studies in this area, we focus on learners from the French-speaking world: France and French-speaking European countries, the Caribbean, North Africa, and Central and West Africa. Results show that the largest gaps in MOOC achievements occur between 1) learners from partner institutions versus self-enrolled learners 2) learners from European countries versus low- and middle-income countries, and 3) learners who are professionally active versus inactive learners (i.e., with available time). Finally, we used the CHAID data-mining method to analyze the main characteristics and discriminant factors of MOOC learner performance and dropout.

Prerequisite-related MOOC recommendation on learning path locating

Prerequisite inadequacy causes more MOOC drop-out. As an effective method interfering with learning process, existing MOOC recommendation is mainly about subsequent learning objects that have not been learned before. This paper proposes a locating-based MOOC recommendation method with consideration on prerequisite relationship. It locates the target learner’s learning paths and provides prerequisite recommendation for unqualified learning objects and subsequent recommendation for the qualified objects. Experiments on real-world data show both the accuracy and learning performance improvement of our recommendation method.

Prediction in MOOCs: A Review and Future Research Directions

This paper surveys the state of the art on prediction in MOOCs through a systematic literature review (SLR). The main objectives are: first, to identify the characteristics of the MOOCs used for prediction, second, to describe the prediction outcomes, third, to classify the prediction features, fourth, to determine the techniques used to predict the variables, and, fifth, to identify the metrics used to evaluate the predictive models. Results show there is strong interest in predicting dropouts 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.).

Embracing Dropouts in MOOCs: Exploring Potentials of Invisible Learners

The objective of the paper is to examine how and what the non-completing participants of MOOCs learn. In this paper we term them invisible learners. The paper presents a qualitative study of learning activities and outcomes of invisible learners. The study consists of 11 interviews with MOOC participants and a survey answered by 51 participants. The results of the study show that invisible learners learn by 1) reading and watching, 2) following and being part of, 3) networking, 4) reflecting and 5) applying. Further, the study shows that the learning outcomes of the invisible learners can be described as 1) inspiration, 2) update, and 3) input for practice. Invisible learners show signs of self-governance by choosing what is relevant to them, and initiating their own learning activities in relation to their own practice. The paper concludes that there are educational potentials of the activities of invisible learners. The study shows that the course format may not be suitable for invisible learners that do not wish to do assignments and follow specific learning objectives. Rather, the educational potential is to provide invisible learners with relevant input to their own practices. To accommodate invisible learners, the challenge is to design courses that provide input and inspiration to learners’ own practices without prescribing what they will learn.

Who Will Be the Next to Drop Out? Anticipating Dropouts in MOOCs with Multi-View Features

Who Will Be the Next to Drop Out? Anticipating Dropouts in MOOCs with Multi-View Features

Student engagement in massive open online courses

Completion rates in massive open online courses MOOCs are disturbingly low. Existing analysis has focused on patterns of resource access and prediction of drop-out using learning analytics. In contrast, the effectiveness of teaching programs in traditional higher education HE settings internationally is increasingly assessed by surveys measuring student engagement. The conceptualisation of engagement used is much richer and more informative than the way the term is currently interpreted in the context of MOOCs. This paper considers MOOC participation, learning and drop-out in the context of this richer conceptualisation of student engagement. MOOC pedagogy and practice are examined and we evaluate how far HE engagement measures can be successfully used in the MOOC context. We identify the need for a MOOC engagement model and suggest recommendations for basic, initial steps which MOOC developers can make towards improving engagement.

A Study of Performance Comparison of MOOC Dropout Prediction utilizing Machine Learning

A Study of Performance Comparison of MOOC Dropout Prediction utilizing Machine Learning