Survey and Comparison of Deep Learning Applications to Improve MOOC
Acceptability (The HOOK Project)
Sergio Simonian* and Serge Miranda
CIFRE Researcher, Datum Academy and University Cote d’Azur, I3S CNRS Research
Laboratory, France and Professor Serge Miranda University Côte d’Azur, Nice, France
*Corresponding Author: Sergio Simonian, CIFRE Researcher, Datum Academy and University Cote d’Azur, I3S CNRS Research
Laboratory, France and Professor Serge Miranda University Côte d’Azur, Nice, France
Received:
August 09, 2021; Published: November 30, 2021
Abstract
Massively Open Online Courses (MOOCs) have been demonstrating their potential to transform traditional online education since their disruption in 2012 with two major features : instructor tutoring and social networking of learners. However some drawback lies in their completion and student success rate remaining very low. In this article, we are focusing on deep learning applications to analyze MOOC data and generate real-time indicators for learners and online professors to improve MOOC acceptability. For this survey we searched for relevant articles using Google Scholar (during the period 2017-2021) and the ERIC database (period 2019-2021) and selected twenty-one articles that demonstrated deep learning methods for MOOC approach improvement. We categorized them into three areas: “MOOC student final outcome prediction” (twelve articles), “MOOC forum post classification” (six articles), and “MOOC student current/next outcome prediction and recommendation” (three articles). We conclude that section by identifying that most deep learning architectures built for these applications focus on student final outcome prediction and use variants of recurrent neural networks (RNN). We also remark that the most occurring datasets were the Stanford MOOC Posts dataset and OULAD. Then in the second part of this article, we functionally compare these major deep learning platforms for MOOC improvement with the one we are building with France Université Numérique(FUN) named HOOK (Human Open Online Knowledge) platform.
Keywords: MOOC (Massive Open Online Courses); E-learning, Online Learning, Big Data; AI, Machine Learning; Deep Learning
References
- , et al. “Predicting At-Risk Students Using Clickstream Data in the Virtual Learning Environment”. Sustainability 11.24 (2019): 7238.
- Booth T. “Deep Learning with Python: A Hands-On Guide for Beginners CA” (2019).
- Boullier Dominique. “Moocs, en attendant l’innovation”. Distances et médiation des savoirs (2014).
- , et al. “Attention-Based Hierarchical Recurrent Neural Networks for MOOC Forum Posts Analysis”. Journal of Ambient Intelligence and Humanized Computing (2020).
- Chen Jing., et al. “Co-Training Semi-Supervised Deep Learning for Sentiment Classification of MOOC Forum Posts”. Symmetry1 (2019): 8.
- Comprendre la CULTURE NUMÉRIQUE. Direction Pauline Escande Gauquié et Bertrand Naivin, Éditions DUNOD, Septembre 2019 (Chapitre de Serge Miranda. QR Code et communacteurs du big data (2019): 144-159.
- Davis Dan., et al. “Follow the Successful Crowd”. Proceedings of the Seventh International Learning Analytics and amp; Knowledge Conference (2017).
- Deep Bridge project. “Pipeline architecture for Deep Learning analysis of scanners images for brain stroke detection” Benjamin Renaut (MBDS, UCA), Hava Chapchoueva (MBDS, UCA), Sergei Gorianin (ECRIN, ESTIA), Pr Elixene Jean Baptiste (CHU Nice), Pr Serge Miranda (MBDS, UCA)
- Duru I., et al. “Deep Learning for Discussion-Based Cross-Domain Performance Prediction of MOOC Learners Grouped by Language on Future Learn”. The Arabian Journal for Science and Engineering 46 (2021): 3613-3629.
- Foster D. “Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play”. Sebastopol, CA: O'Reilly Media (2019).
- Goldberg Y. “A primer on neural network models for natural language”. Processing (2015).
- Guo C and Berkhahn F. “Entity Embeddings of Categorical Variables” (2016).
- Guo Shou Xi., et al. “Attention-Based Character-Word Hybrid Neural Networks with Semantic and Structural Information for Identifying of Urgent Posts in MOOC Discussion Forums”. IEEE Access 7 (2019): 120522-120532.
- He Yanbai., et al. “Online At-Risk Student Identification Using RNN-GRU Joint Neural Networks”. Information10 (2020): 474.
- Ian Goodfellow., et al. “Deep Learning”. MIT Press (2016).
- Karimi Hamid., et al. “Online Academic Course Performance Prediction using Relational Graph Convolutional Neural Network”. EDM (2020).
- Kim Byung-Hack., et al. “GritNet: Student Performance Prediction with Deep Learning”. ArXiv abs/1804.07405 (2018).
- KÅ‘rösi Gábor and Richard Farkas. “MOOC Performance Prediction by Deep Learning from Raw Clickstream Data”. Communications in Computer and Information Science Advances in Computing and Data Sciences (2020): 474-485.
- Maupetit J. “ATELIER N°5 - Initiation à Potsie, la plateforme FUN de learning analytics” (2021).
- Pardos Zachary A., et al. “Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework”. Proceedings of the Fourth. ACM Conference on Learning @ Scale (2017).
- Plank B., et al. “Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss”. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics 2 (2016).
- Schmidhuber J.” Deep learning in neural networks: An overview”. Neural Networks 61 (2015): 85-117.
- Shah D. “By The Numbers: MOOCs in 2020”. Class Central (2020).
- Shah D. “The Second Year of the MOOC: A Review of MOOC Stats and Trends in 2020”. Class Central (2020).
- “The Stanford MOOCPosts Dataset”.
- Tu Yuwei., et al. “A Deep Learning Approach to Behavior-Based Learner Modeling”. ArXiv abs/2001.08328 (2020).
- “Université Côte d'Azur lance son premier master informatique en ligne”. Université Côte d'Azur (2019).
- Waheed Hajra., et al. “Predicting Academic Performance of Students from VLE Big Data Using Deep Learning Models”. Computers in Human Behavior 104 (2020): 106189.
- Wang Jingjing., et al. “Top-N personalized recommendation with graph neural networks in MOOCs”. Computers and Education: Artificial Intelligence 2 (2021).
- Wang L., et al. “Learning to Represent Student Knowledge on Programming Exercises Using Deep Learning”. EDM (2017).
- Wang Wei., et al. “Deep Model for Dropout Prediction in MOOCs”. Proceedings of the 2nd International Conference on Crowd Science and Engineering-ICCSE' 17 (2017).
- Wei Xiaocong., et al. “A Convolution-LSTM-Based Deep Neural Network for Cross-Domain MOOC Forum Post Classification”. Information3 (2017): 92.
- X Sun., et al. “Identification of urgent posts in MOOC discussion forums using an improved RCNN”. IEEE World Conference on Engineering Education (EDUNINE) (2019): 1-5.
- Xing Wanli and Dongping Du. “Dropout Prediction in MOOCs: Using Deep Learning for Personalized Intervention”. Journal of Educational Computing Research3 (2018): 547-570.
- Yin S., et al. “The analysis and early warning of student loss in MOOC course”. Proceedings of the ACM Turing Celebration Conference-China (2019).
- Yu Jialin., et al. “Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums”. ArXiv abs 2104.12643 (2021).
- Zhang A., et al. “Dive into Deep Learning” (2020).
- Zhang, Yuan and JIANG Wenbo. “Score Prediction Model of MOOCs Learners Based on Neural Network”. International Journal of Emerging Technologies in Learning10 (2018): 171-182.
- Zhou and Chellappa. "Computation of optical flow using a neural network”. IEEE International Conference on Neural Networks 2 (1988): 71-78.
Citation
Copyright