Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence
Early prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performa...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/4/1885 |
| _version_ | 1797483047909588992 |
|---|---|
| author | Hsing-Chung Chen Eko Prasetyo Shian-Shyong Tseng Karisma Trinanda Putra Prayitno Sri Suning Kusumawardani Chien-Erh Weng |
| author_facet | Hsing-Chung Chen Eko Prasetyo Shian-Shyong Tseng Karisma Trinanda Putra Prayitno Sri Suning Kusumawardani Chien-Erh Weng |
| author_sort | Hsing-Chung Chen |
| collection | DOAJ |
| description | Early prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performance in the early weeks due to the lack of students’ activities’ data in a week-wise timely manner (i.e., spatiotemporal feature issues). Furthermore, the imbalanced data distribution in the VLE impacts the prediction model performance. Thus, there are severe challenges in handling spatiotemporal features, imbalanced data sets, and a lack of explainability for enhancing the confidence of the prediction system. Therefore, an intelligent framework for explainable student performance prediction (ESPP) is proposed in this study in order to provide the interpretability of the prediction results. First, this framework utilized a time-series weekly student activity data set and dealt with the VLE imbalanced data distribution using a hybrid data sampling method. Then, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) was employed to extract the spatiotemporal features and develop the early prediction deep learning (DL) model. Finally, the DL model was explained by visualizing and analyzing typical predictions, students’ activities’ maps, and feature importance. The numerical results of cross-validation showed that the proposed new DL model (i.e., the combined CNN-LSTM and ConvLSTM), in the early prediction cases, performed better than the baseline models of LSTM, support vector machine (SVM), and logistic regression (LR) models. |
| first_indexed | 2024-03-09T22:42:17Z |
| format | Article |
| id | doaj.art-1ca140a35a8d4071ad36e55897c2de66 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:42:17Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1ca140a35a8d4071ad36e55897c2de662023-11-23T18:35:42ZengMDPI AGApplied Sciences2076-34172022-02-01124188510.3390/app12041885Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial IntelligenceHsing-Chung Chen0Eko Prasetyo1Shian-Shyong Tseng2Karisma Trinanda Putra3Prayitno4Sri Suning Kusumawardani5Chien-Erh Weng6Department of Computer Science and Information Engineering, Asia University, Taichung City 413, TaiwanDepartment of Computer Science and Information Engineering, Asia University, Taichung City 413, TaiwanDepartment of M-Commerce and Multimedia Applications, Asia University, Taichung City 413, TaiwanDepartment of Computer Science and Information Engineering, Asia University, Taichung City 413, TaiwanDepartment of Computer Science and Information Engineering, Asia University, Taichung City 413, TaiwanDepartment of Electrical and Information Engineering, Universitas Gadjah Mada, Yogyakarta 55281, IndonesiaDepartment of Telecommunication Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 811, TaiwanEarly prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performance in the early weeks due to the lack of students’ activities’ data in a week-wise timely manner (i.e., spatiotemporal feature issues). Furthermore, the imbalanced data distribution in the VLE impacts the prediction model performance. Thus, there are severe challenges in handling spatiotemporal features, imbalanced data sets, and a lack of explainability for enhancing the confidence of the prediction system. Therefore, an intelligent framework for explainable student performance prediction (ESPP) is proposed in this study in order to provide the interpretability of the prediction results. First, this framework utilized a time-series weekly student activity data set and dealt with the VLE imbalanced data distribution using a hybrid data sampling method. Then, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) was employed to extract the spatiotemporal features and develop the early prediction deep learning (DL) model. Finally, the DL model was explained by visualizing and analyzing typical predictions, students’ activities’ maps, and feature importance. The numerical results of cross-validation showed that the proposed new DL model (i.e., the combined CNN-LSTM and ConvLSTM), in the early prediction cases, performed better than the baseline models of LSTM, support vector machine (SVM), and logistic regression (LR) models.https://www.mdpi.com/2076-3417/12/4/1885imbalanced data distributionexplainable student performance predictionfeature importance |
| spellingShingle | Hsing-Chung Chen Eko Prasetyo Shian-Shyong Tseng Karisma Trinanda Putra Prayitno Sri Suning Kusumawardani Chien-Erh Weng Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence Applied Sciences imbalanced data distribution explainable student performance prediction feature importance |
| title | Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence |
| title_full | Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence |
| title_fullStr | Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence |
| title_full_unstemmed | Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence |
| title_short | Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence |
| title_sort | week wise student performance early prediction in virtual learning environment using a deep explainable artificial intelligence |
| topic | imbalanced data distribution explainable student performance prediction feature importance |
| url | https://www.mdpi.com/2076-3417/12/4/1885 |
| work_keys_str_mv | AT hsingchungchen weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT ekoprasetyo weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT shianshyongtseng weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT karismatrinandaputra weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT prayitno weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT srisuningkusumawardani weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence AT chienerhweng weekwisestudentperformanceearlypredictioninvirtuallearningenvironmentusingadeepexplainableartificialintelligence |