Deep Learning for Dropout Prediction in MOOCs

Sun, Di; Mao, Yueheng; Du, Junlei; Xu, Pengfei; Zheng, Qinhua; Sun, Hong

doi:10.1109/eitt.2019.00025

Cited by 26 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This phenomenon is due to the fact that the course duration is only five weeks, and the number of behavioral characteristics of some students drops significantly after the course, leading to partial data missing in the fifth week, which has a certain impact on the performance of the model. From the recently published literature, this paper selected five representative MOOC dropout prediction models for comparison tests with the FWTS-CNN model as follows: the logistic regression-based machine learning MOOC dropout prediction model proposed by Qiu et al [28], the support vector machine based machine learning MOOC dropout prediction model proposed by Kloft et al [22] , the LSTM neural network MOOC dropout prediction model proposed by Wang et al [44], the CNN combined with LSTM MOOC dropout prediction model proposed by Sun Xia et al [45], and the time series-based CNN MOOC dropout prediction model proposed by Qiu et al [15]. The KDD CUP 2015 dataset was used as the original dataset for all models in the experiment.…”

Section: Resultsmentioning

confidence: 99%

MOOC Dropout Prediction Using FWTS-CNN Model Based on Fused Feature Weighting and Time Series

et al. 2020

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

MOOC Dropout Prediction Using FWTS-CNN Model Based on Fused Feature Weighting and Time Series

et al. 2020

View full text Add to dashboard Cite

“…However, RNN models generally suffer from long-term dependency on learning behaviours in these studies, leading to limited prediction performance. Additionally, all these studies [9,14,44,50] stress more temporal characteristics, but neglect the fact that students are likely to exhibit similar learning patterns during a period.…”

Section: Learning Activity-based Predictionmentioning

confidence: 99%

A Brief Survey of Deep Learning Approaches for Learning Analytics on MOOCs

Sun

Harit

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Massive Open Online Course (MOOC) systems have become prevalent in recent years and draw more attention, a.o., due to the coronavirus pandemic's impact. However, there is a well-known higher chance of dropout from MOOCs than from conventional off-line courses. Researchers have implemented extensive methods to explore the reasons behind learner attrition or lack of interest to apply timely interventions. The recent success of neural networks has revolutionised extensive Learning Analytics (LA) tasks. More recently, the associated deep learning techniques are increasingly deployed to address the dropout prediction problem. This survey gives a timely and succinct overview of deep learning techniques for MOOCs' learning analytics. We mainly analyse the trends of feature processing and the model design in dropout prediction, respectively. Moreover, the recent incremental improvements over existing deep learning techniques and the commonly used public data sets have been presented. Finally, the paper proposes three future research directions in the field: knowledge graphs with learning analytics, comprehensive social network analysis, composite behavioural analysis.

show abstract

“…Many researchers employed techniques without manual feature engineering processes to predict dropout. Few previous works explored deep neural network (DNN) model [28], recurrent neural network (RNN) model [27,54], and convolutional neural networks (CNN) followed by RNN [42,53]. Yet, all of these recent models, so far, have given suboptimal performance.…”

Section: Video-clickstreammentioning

confidence: 99%

Visual analytics of video‐clickstream data and prediction of learners' performance using deep learning models in MOOCs' courses

Mubarak

Cao

Zhang

2020

Comp Applic In Engineering

View full text Add to dashboard Cite

The big data stored in massive open online course (MOOC) platforms have become a posed challenge in the Learning Analytics field to analyze the learning behavior of learners, and predict their respective performance, related especially to video lecture data, since most learners view the same online lecture videos. This helps to conduct a comprehensive analysis of such behaviors and explore various learning patterns in MOOC video interactions. This paper aims at presenting a visual analysis, which enables course instructors and education experts to analyze clickstream data that were generated by learner interaction with course videos. It also aims at predicting learner performance, which is a vital decision-making problem, by addressing their issues and improving the educational process. This paper uses a long short-term memory network (LSTM) on implicit features extracted from videoclickstreams data to predict learners' performance and enable instructors to make measures for timely intervention. Results show that the accuracy rate of the proposed model is 89%-95% throughout course weeks. The proposed LSTM model outperforms baseline Deep learning (GRU) and simple recurrent neural network by accuracy of 90.30% in the "Mining of Massive Datasets" course, and the "Automata Theory" accuracy is 89%.

show abstract

Deep Learning for Dropout Prediction in MOOCs

Cited by 26 publications

References 9 publications

MOOC Dropout Prediction Using FWTS-CNN Model Based on Fused Feature Weighting and Time Series

MOOC Dropout Prediction Using FWTS-CNN Model Based on Fused Feature Weighting and Time Series

A Brief Survey of Deep Learning Approaches for Learning Analytics on MOOCs

Visual analytics of video‐clickstream data and prediction of learners' performance using deep learning models in MOOCs' courses

Contact Info

Product

Resources

About