Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach
Learning patterns are crucial for predicting student dropout in educational settings, providing insights into students’ behaviors and motivations. However, existing mainstream dropout prediction models have limitations in effectively mining these learning patterns and cannot mine these learning patt...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/24/4977 |
| _version_ | 1797380158932385792 |
|---|---|
| author | Tiancheng Zhang Hengyu Liu Jiale Tao Yuyang Wang Minghe Yu Hui Chen Ge Yu |
| author_facet | Tiancheng Zhang Hengyu Liu Jiale Tao Yuyang Wang Minghe Yu Hui Chen Ge Yu |
| author_sort | Tiancheng Zhang |
| collection | DOAJ |
| description | Learning patterns are crucial for predicting student dropout in educational settings, providing insights into students’ behaviors and motivations. However, existing mainstream dropout prediction models have limitations in effectively mining these learning patterns and cannot mine these learning patterns in large-scale, distributed educational datasets. In this study, we analyze the representations of mainstream models and identify their inability to capture students’ distinct learning patterns and personalized variations across courses. Addressing these challenges, our study adopts a federated learning approach, tailoring the analysis to leverage distributed data while maintaining privacy and decentralization. We introduce the Federated Learning Pattern Aware Dropout Prediction Model (FLPADPM), which utilizes a one-dimensional convolutional neural network (CNN) and a bidirectional long short-term memory (LSTM) layer within a federated learning framework. This model is designed to effectively capture nuanced learning patterns and adapt to variations across diverse educational settings. To evaluate the performance of LPADPM, we conduct an empirical evaluation using the KDD Cup 2015 and XuetangX datasets. Our results demonstrate that LPADPM outperforms state-of-the-art models in accurately predicting student dropout behavior. Furthermore, we visualize the representations generated by LPADPM, which confirm its ability to effectively mine learning patterns in different courses. Our results showcase the model’s ability to capture and analyze learning patterns across various courses and institutions within a federated learning context. |
| first_indexed | 2024-03-08T20:34:18Z |
| format | Article |
| id | doaj.art-e03c8398527e4f96baa46a047da5bd5a |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T20:34:18Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-e03c8398527e4f96baa46a047da5bd5a2023-12-22T14:23:29ZengMDPI AGMathematics2227-73902023-12-011124497710.3390/math11244977Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning ApproachTiancheng Zhang0Hengyu Liu1Jiale Tao2Yuyang Wang3Minghe Yu4Hui Chen5Ge Yu6School of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaSchool of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaSchool of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW 2109, AustraliaSchool of Computer Science and Engineering, Northeast University, Shenyang 110819, ChinaLearning patterns are crucial for predicting student dropout in educational settings, providing insights into students’ behaviors and motivations. However, existing mainstream dropout prediction models have limitations in effectively mining these learning patterns and cannot mine these learning patterns in large-scale, distributed educational datasets. In this study, we analyze the representations of mainstream models and identify their inability to capture students’ distinct learning patterns and personalized variations across courses. Addressing these challenges, our study adopts a federated learning approach, tailoring the analysis to leverage distributed data while maintaining privacy and decentralization. We introduce the Federated Learning Pattern Aware Dropout Prediction Model (FLPADPM), which utilizes a one-dimensional convolutional neural network (CNN) and a bidirectional long short-term memory (LSTM) layer within a federated learning framework. This model is designed to effectively capture nuanced learning patterns and adapt to variations across diverse educational settings. To evaluate the performance of LPADPM, we conduct an empirical evaluation using the KDD Cup 2015 and XuetangX datasets. Our results demonstrate that LPADPM outperforms state-of-the-art models in accurately predicting student dropout behavior. Furthermore, we visualize the representations generated by LPADPM, which confirm its ability to effectively mine learning patterns in different courses. Our results showcase the model’s ability to capture and analyze learning patterns across various courses and institutions within a federated learning context.https://www.mdpi.com/2227-7390/11/24/4977data analysisfederated learningmachine learningdeep learningdropout prediction |
| spellingShingle | Tiancheng Zhang Hengyu Liu Jiale Tao Yuyang Wang Minghe Yu Hui Chen Ge Yu Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach Mathematics data analysis federated learning machine learning deep learning dropout prediction |
| title | Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach |
| title_full | Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach |
| title_fullStr | Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach |
| title_full_unstemmed | Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach |
| title_short | Enhancing Dropout Prediction in Distributed Educational Data Using Learning Pattern Awareness: A Federated Learning Approach |
| title_sort | enhancing dropout prediction in distributed educational data using learning pattern awareness a federated learning approach |
| topic | data analysis federated learning machine learning deep learning dropout prediction |
| url | https://www.mdpi.com/2227-7390/11/24/4977 |
| work_keys_str_mv | AT tianchengzhang enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT hengyuliu enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT jialetao enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT yuyangwang enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT mingheyu enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT huichen enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach AT geyu enhancingdropoutpredictionindistributededucationaldatausinglearningpatternawarenessafederatedlearningapproach |