Predictive learning analytics using deep learning model in MOOCs’ courses videos

Mubarak, Ahmed A.; Cao, Han; Ahmed, Salah

doi:10.1007/s10639-020-10273-6

Cited by 81 publications

(54 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The author utilizes a deep LSTM model in [29] on a collection of features obtained from video clickstream data. The underlying goal is to predict learners' weekly perfor-mance and allow teachers to initiate appropriate measures for timely intervention.…”

Section: A Learning Analyticsmentioning

confidence: 99%

Integrating Learning Analytics and Collaborative Learning for Improving Student’s Academic Performance

et al. 2021

View full text Add to dashboard Cite

Big data analytics has shown tremendous success in several fields such as businesses, agriculture, health, and meteorology, and education is no exception. Concerning its role in education, it is used to boost students' learning process by predicting their performance in advance and adapting the relevant instructional design strategies. This study primarily intends to develop a system that can predict students' performance and help teachers to timely introduce corrective interventions to uplift the performance of low-performing students. As a secondary part of this research, it also explores the potential of collaborative learning as an intervention to act in combination with the prediction system to improve the performance of students. To support such changes, a visualization system is also developed to track and monitor the performance of students, groups, and overall class to help teachers in the regrouping of students concerning their performance. Several well-known machine learning models are applied to predict students performance. Results suggest that experimental groups performed better after treatment than before treatment. The students who took part in each class activity, prepared and submitted their tasks perform much better than other students. Overall, the study found that collaborative learning methods play a significant role to enhance the learning capability of the students.

show abstract

Section: A Learning Analyticsmentioning

confidence: 99%

Integrating Learning Analytics and Collaborative Learning for Improving Student’s Academic Performance

et al. 2021

View full text Add to dashboard Cite

show abstract

“…There is also a danger that a reductionist view of the student could fail to see all the student components contributing to student success. Actions should be taken to encourage educators to engage with learning analytics technology and apply the results to their teaching practices (Balica, 2018;Islam et al, 2021;Mubarak et al, 2021;Prinsloo & Slade, 2017;Ranjeeth et al, 2020;Renties et al, 2020).…”

Section: Swot Analysis Of Industry 40 and The Impact On Learning Analyticsmentioning

confidence: 99%

Industry 4.0: Learning Analytics Using Artificial Intelligence and Advanced Industry Applications

Bakkar

Axmann²

2021

Manage Your Own Learning Analytics

View full text Add to dashboard Cite

Learning analytics is a crucial factor in measuring the effectiveness of any educational programme. Industry 4.0, mainly artificial intelligence (AI) applications are integrated into the digital pedagogical techniques and the learning analytics that further enhance and develop the online instructional materials. Therefore, it is crucial to explain the usage of those technologies used for the learning analytics associated with the educational system to show the different use of AI. This book chapter explains: the meaning of the learning analytics in Industry 4.0 and education and its affiliated areas; AI and its related areas with examples from state-of-the-art corporate applications and solutions based on AI technologies integrated into the learning analytics.

show abstract

“…Recent video-learning analytics research covered three directions: First, visual content analysis, which included visible pattern recognition, transcript analysis, and video indexing [45,50]. Second, explicit learners' data (explicit video analytics) such as clicking buttons, views, and votes [13,24,38,39], and data's influence on the learning result. The explicit learner data analytics provide inferences on video usage range and popularity.…”

Section: Video-clickstreammentioning

confidence: 99%

“…On the other hand, it lacks in-depth video interaction analysis to discover learner behavior when he/she is interested, confused, or misunderstood. Third, implicit learners' data (implicit video analytics) such as interaction records in-depth videos [38,39,46,61,8]. The implicit video analytics can be used in depth-video interaction to identify the kind of difficulties that may encounter learners while watching the video and the degree of the perceived video difficulty they indicate.…”

Section: Video-clickstreammentioning

confidence: 99%

“…); and (c) prepare interactive activities like in-video quizzes. Nevertheless, there are limited studies on exposing various complex aspects of clickstream interactions resulting from students' activities within different MOOC videos [22,38,39,48,49]. Furthermore, in video, dropout is one of the remaining challenging issues in spite of video design considerations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Self Cite

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

Predictive learning analytics using deep learning model in MOOCs’ courses videos

Cited by 81 publications

References 40 publications

Integrating Learning Analytics and Collaborative Learning for Improving Student’s Academic Performance

Integrating Learning Analytics and Collaborative Learning for Improving Student’s Academic Performance

Industry 4.0: Learning Analytics Using Artificial Intelligence and Advanced Industry Applications

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

Contact Info

Product

Resources

About