The advent of big data and artificial intelligence (AI) technologies has catalyzed transformative changes across various sectors, including education. We propose two graph neural network-based models—MTGNN and DAGNN—for improving the prediction of student performance in educational settings. These models are evaluated using the Open University Learning Analytics Dataset (OULAD). MTGNN leverages multiple similarity metrics to build student relationship graphs that capture latent patterns, improving prediction outcomes. DAGNN enhances this approach by adding attention mechanisms and graph augmentation, leading to more accurate and robust predictions. Our experimental results show that both models outperform conventional baselines, especially in identifying at-risk students. This work demonstrates the potential of GNNs to transform educational analytics by modeling complex student data, enabling more effective, personalized interventions.
ZhouJCuiGHuS, et al.Graph neural networks: a review of methods and applications. AI open2020; 1: 57–81.
2.
SunXZhangY. An improved BP neural network algorithm for the evaluation system of innovation and entrepreneurship education in colleges and universities. Mob Inf Syst2022; 2022: 1–10.
3.
ZhengY. A transfer learning-based model for assessing university students' innovation and entrepreneurship. Int J Comput Syst Eng2024; 8(1-2): 66–74.
4.
WangCDongYXiaY, et al.Management and entrepreneurship management mechanism of college students based on support vector machine algorithm. Comput Intell2022; 38(3): 842–854.
5.
HuangZLiuG. Prediction model of college students entrepreneurship ability based on artificial intelligence and fuzzy logic model. J Intell Fuzzy Syst2021; 40(2): 2541–2552.
6.
GengL. The recommendation system of innovation and entrepreneurship education resources in universities based on improved co llaborative filtering model. Comput Intell Neurosci2022; 2022: 7228833.
7.
WuLCuiPPeiJ, et al.Graph neural networks: foundation, frontiers and applicationsProceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, 2022.
8.
LiJZhaoY. Construction of innovation and entrepreneurship platform based on deep learning algorithm. Sci Program2021; 2021: 1–7.
9.
MengXRenGHuangW. A quantitative enhancement mechanism of university students’ employability and entrepreneurship based on deep learning in the context of the digital era. Sci Program2021; 2021: 1–12.
10.
WangMShaoYFuS, et al.The influence of college students’ innovation and entrepreneurship intention in the art field of art film and television appreciation by deep learning under entrepreneurial psychology. Front Psychol2022; 13: 900176.
11.
ZengYWeiZYuW, et al.Spatial transcriptomics prediction from histology jointly through transformer and graph neural networks. Briefings Bioinf2022; 23(5): bbac297.
12.
YuMZhangZLiX, et al.Superposition graph neural network for offshore wind power prediction. Future Gener Comput Syst2020; 113: 145–157.
13.
LinWWuDBouletB. Spatial-temporal residential short-term load forecasting via graph neural networks. IEEE Trans Smart Grid2021; 12(6): 5373–5384.
14.
JainLKataryaRSachdevaS. Opinion leaders for information diffusion using graph neural network in online social networks. ACM Trans Web2023; 17(2): 1–37.
15.
LiX-SLiuXLuL, et al.Multiphysical graph neural network (MP-GNN) for COVID-19 drug design. Briefings Bioinf2022; 23(4): bbac231.
16.
JagvaralBLeeWKRohJS, et al.Path-based reasoning approach for knowledge graph completion using CNN-BiLSTM with attention mechanism[J/OL]. Expert Syst Appl2020; 142: 112960.
17.
XiangSChengDShangC, et al.Temporal and heterogeneous graph neural network for financial time series prediction. Proceedings of the 31st ACM international conference on information & knowledge management, 2022.
18.
KhanAGhoshSK. Student performance analysis and prediction in classroom learning: a review of educational data mining studies. Educ Inf Technol2021; 26(1): 205–240.
19.
SwamyV. Evaluating the explainers: black-box explainable machine learning for student success prediction in MOOCs. arXiv preprint arXiv:2207.005512022.
20.
BlouinD. Accreditation of Canadian undergraduate medical education programs: a study of measures of effectiveness. Acad Med2020; 95(6): 931–937.
21.
MacCannCJiangYBrownLER, et al.Emotional intelligence predicts academic performance: a meta-analysis. Psychol Bull2020; 146(2): 150–186.
22.
MammadovS. Big five personality traits and academic performance: a meta‐analysis. J Pers2022; 90(2): 222–255.
23.
AlhakbaniHAAlnassarFM. Open learning analytics: a systematic review of benchmark studies using open university learning analytics dataset (OULAD). Proceedings of the 2022 7th international conference on machine learning technologies, 2022.
24.
KuzilekJHlostaMZdrahalZ. Open university learning analytics dataset. Sci Data2017; 4(1): 1–8.
25.
UppalMGuptaDGoyalN, et al.A real‐time data monitoring framework for predictive maintenance based on the internet of things. Complexity2023; 1(2023): 9991029–9991114.
26.
AnandDSinghAAlsubhiK, et al.A smart cloud and IoVT-based kernel adaptive filtering framework for parking prediction. IEEE Trans Intell Transport Syst2022; 24(3): 2737–2745.
27.
SwamyVRadmehrBKrcoN, et al.Evaluating the explainers: black-box explainable machine learning for student success prediction in MOOCs. arXiv preprint arXiv:2207.00551. 2022.
28.
XiangSChengDShangC, et al.Temporal and heterogeneous graph neural network for financial time series prediction. Proceedings of the 31st ACM international conference on information & knowledge management, 2022.
29.
JainLKataryaRSachdevaS. Opinion leaders for information diffusion using graph neural network in online social networks. ACM Trans Web2023; 17: 1–37.
30.
ZhangQYuKGuoZ, et al.Graph neural network-driven traffic forecasting for the connected internet of vehicles. IEEE Trans Netw Sci Eng2021; 9(5): 3015–3027.
