Frontiers in Educational Research, 2026, 9(8); doi: 10.25236/FER.2026.090803.
Shaohong Chen1, Yonggui Luo1, Lingling Dai2
1School of Accounting, Guangzhou Huashang College, Guangzhou, Guangdong, China
2School of Teacher Education, Guangzhou Huashang College, Guangzhou, Guangdong, China
Assessing student party member development, particularly political literacy, in Chinese private universities is hampered by exam centric, subjective methods that ignore unstructured data. We propose an explainable hybrid CEEMDAN XGBoost LSTM model within a three dimensional framework (political Literacy, practical performance, Industry Education Integration). CEEMDAN decomposes evaluation sequences; LSTM captures dynamic patterns while XGBoost extracts static features, with dynamic fusion and SHAP for interpretability. On 1,200 records from five private universities, our model achieves 91.6% accuracy and 0.953 AUC, significantly outperforming baselines. SHAP reveals Industry Education Integration contributes 28.3%—far exceeding the 9.7% in public institutions—and highlights synergy with political literacy. Deployed on edge devices, it reduces latency and improves candidate conversion and staff acceptance. This framework provides a robust, transparent tool for objective, data driven party building management.
private Universities, party Member Development, Intelligent Evaluation, Explainable AI (XAI), Hybrid Model, XGBoost-LSTM
Shaohong Chen, Yonggui Luo, Lingling Dai. An Explainable CEEMDAN-XGBoost-LSTM Hybrid Model for Assessing Party Member Development in Chinese Private Universities. Frontiers in Educational Research (2026), Vol. 9, Issue 8: 14-28. https://doi.org/10.25236/FER.2026.090803.
[1] Jia Zheng. practical Exploration of Informatisation and Intelligence in Grassroots party Building at Higher Education Institutions [J]. School party Building and Ideological Education, 2024, (24): 26-28. DOI:10.19865/j.cnki.xxdj.2024.24.007.
[2] Ren Yanfeng, An Junxue, Wei Zhongmin. Practical Exploration of Digital party Building Empowering High-Quality Development of University party Building [J]. Journal of Shenyang Agricultural University (Social Sciences Edition), 2024, 26(1): 23-30. DOI:10.3969/j.issn.1008-9713.2024.01.004.
[3] Wang Liming, Gao pan. Research on Enhancing the Quality Control System for Student party Member Development in private Universities: A Case Study of the Southern Business School at Guangdong University of Foreign Studies [J]. Forum on Education and Teaching, 2016(22): 246-247. DOI:10.3969/j.issn.1674-9324.
[4] Shao Mingying, Wu Jiarui. Research on Standards and Quality Status of Student party Member Development in Higher Education Institutions in the New Era: A Sampling Survey of 10 Universities in Beijing [J]. Research on Ideological Education, 2021(4):146-149.
[5] Joksimovic S, Gasevic D, Loughin T M, et al. Learning at distance: Effects of interaction traces on academic achievement [J]. Computers & Education, 2015, 87(SEp.): 204-217. DOI:10.1016/j.compedu.2015.07.002.
[6] Butt N A, Mahmood Z, Shakeel K, et al. performance prediction of students in higher education using multi-model ensemble approach[J]. IEEE Access, 2023, 11: 136091-136108.
[7] Chango W, Cerezo R, Romero C. Multi-source and multimodal data fusion for predicting academic performance in blended learning university courses[J]. Computers & Electrical Engineering, 2021, 89: 106908.
[8] Baltrušaitis T, Ahuja C, Morency L p. Multimodal machine learning: A survey and taxonomy[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(2): 423-443.
[9] Arrieta A B, Díaz-Rodríguez N, Del Ser J, et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI[J]. Information fusion, 2020, 58: 82-115.
[10] Romero C, Ventura S. Educational data mining and learning analytics: An updated survey[J]. Wiley interdisciplinary reviews: Data mining and knowledge discovery, 2020, 10(3): e1355.
[11] Sharma K, Giannakos M, Dillenbourg p. Eye-tracking and artificial intelligence to enhance motivation and learning[J]. Smart Learning Environments, 2020, 7(1): 13.
[12] Zheng Zidong. Research on Quality Assurance and Evaluation Mechanisms for Developing Student party Members[D]. Chengdu: Sichuan Agricultural University, 2013.
[13] Huang, F. Y. Research on the Construction of Quality Assurance Systems for Student party Member Development in private Higher Education Institutions [J]. Journal of Hubei Open Vocational College, 2021, 34(14): 107-109.
[14] Yi Hui-ling. practical pathways for AI-Empowered Innovation in University party Building Work [J]. Times Report, 2025, (04): 18-20.
[15] Shao Guang. From "Addition" to "Integration": Research on AI-Empowered pathways for Grassroots party Branch Development in Higher Education Institutions [J]. Hongyan Spring and Autumn, 2025(3):108-112.
[16] Luan Chun. Construction and Application of a Multimodal Emotional Dataset for University Students' party Membership Applications [D]. Shandong: Shandong Normal University, 2024.
[17] Chen Min. Research on Student party Member Cultivation Mechanisms in Grassroots party Organisations from a pDCA Cycle Management perspective: A Case Study of Guangdong University of Technology [J]. Journal of Guangdong Transportation Vocational College, 2025, 24(02):120-124.
[18] Wang Rui. Evaluation of party Member Candidates in Logistics Majors Based on TOpSIS [J]. China Storage and Transportation, 2025, (05): 127-128.
[19] Deng Denghua, Yu Mengzhen, He ping. Construction and Application of a Quantitative Assessment System for Developing Student party Members in Higher Education Institutions [J]. University, 2025, (15): 177-180.
[20] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System [C]//Knowledge Discovery and Data Mining. ACM, 2016. DOI:10.1145/2939672.2939785.
[21] Gong Kui, Sun Yu. Research on XGBoost Boosting Methods Based on Gain Statistics [J]. Electronic Technology and Software Engineering, 2021, (11): 154 157.
[22] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[23] Niu Yamin, Zhang Jie, pan Limin, et al. Design of performance Data Analysis Algorithm Integrating Gated Operations and LSTM[J]. Information Technology, 2025(6):76-80. DOI:10.13274/j.cnki.hdzj.2025.06.013.
[24] Greff K, Srivastava R K, Koutník J, et al. LSTM: A search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 28(10): 2222-2232.
[25] Xu Jiangbo, Hou Xinmin, Wu Xiong, Liu Yifan, Sun Guozheng. Research on slope displacement prediction based on the MIC-XGBoost-LSTM model[J]. Journal of Highway and Transportation Engineering, 2024, 37(10): 38-48.
[26] Zhou Z H. Machine learning[M]. Springer nature, 2021.
[27] Xiong Ruiting. Research and Application of Deep Learning-Based Sentiment Analysis of Weibo Text [Doctoral Dissertation]. Nanchang: Nanchang University, 2023.
[28] Lundberg S M, Lee S I. A unified approach to interpreting model predictions[J]. Advances in neural information processing systems, 2017, 30.
[29] Ras G, Van Gerven M, Haselager p. Explanation methods in deep learning: Users, values, concerns and challenges[M]//Explainable and interpretable models in computer vision and machine learning. Cham: Springer International publishing, 2018: 19-36.
[30] Yang Q, Liu Y, Chen T, Tong Y. Federated machine learning: concept and applications [J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 1 19.
[31] Wang Yudong, Li Jiahuan, Yue Xian, Zou Mingheng. prediction of Main Steam pressure in power plant Boilers Based on CEEMDAN Hybrid WTD-XGBoost-LSTM[J]. Electronic Devices, 2024, 47(03): 780-787.
[32] Wang Li, Wang Tao, Xiao Wei, et al. A Bidirectional Feature Selection Algorithm Inspired by XGBoost[J]. Journal of Jilin University: Science Edition, 2021, 59(3):8. DOI:10.13413/ j.cnki.jdxblxb.2020332.
[33] Meng, Xiuying. Quantitative Research on the Recommendation of Development Candidates for University Student party Members [J]. Management Observation, 2016(7):3. DOI:10.3969/j.issn. 1674-2877.2016.07.051.
[34] Ji Yanping. Comparative Study on Academic Adaptation Development Among Undergraduates in private and public Universities [D]. Nanjing: Nanjing Normal University. 2008. DOI:10.7666/d.y1330098.
[35] Liu Huanjiang, Jin Qiyan. Establishing a Quality System for Developing Student party Members in private Universities under the New Era Context [J]. Times Report, 2024(1):53-55.
[36] Li Xiao, He Shuyu, peng Yan, Yang Rongxin, Tao Lu, Lou Tingqi, He Wenqi. An Interpretable Hand-Foot-and-Mouth Disease Outbreak prediction Model Integrating Improved LSTM and XGBoost [J]. Journal of Engineering Sciences, 2025, 47(07): 1525-1535.
[37] Brooks JA, Tzirakis p, Baird A, et al. Deep learning reveals what vocal bursts express in different cultures[J]. Nature Human Behaviour, 2023, 7(2): 240-250.