Student Sentiment Analysis with Co-Curricular Activities and Placement Using Logistic Graph Convolution Neural Network
DOI:
https://doi.org/10.24237/djes.2026.19205Keywords:
Deep Learning, Co-curricular activities, Euclidean Synthetic Minority Over-sampling, L1-regularized Graph Convolution Neural NetworkAbstract
Student feedback sentiment analysis for co-curricular activities, employing deep learning, ascertains and classifies job placements based on students' feedback. Though several works have focused on student sentiment analysis, there remains room to analyze job placement and the effects of co-curricular activities on students' academic performance. This work proposes a method, called L1-Regularized Graph Convolutional Neural Network (L1-GCNN), to identify the relationship between co-curricular activities and students' placement performance. Initially, the raw student placement data is considered as input. After that, Euclidean Synthetic Minority Over-sampling-based pre-processing, including normalization and class balancing, is applied to the student placement dataset. Synthetic samples are generated efficiently, thereby avoiding distortions in local distributions and achieving class-balanced results. Following this, a normalized, class-balanced sample is used to train an L1-regularised Graph Convolutional Neural Network-based Student sentiment analysis, which is then applied to identify the most representative and optimal feature subset for estimating the impact of co-curricular activities on students’ academic performance. Employing the graph structure, the L1-regularised or logistic function highlights the interdependencies between co-curricular metrics and student placement performance via feedback. Moreover, the L1-regularisation function improves the student performance system by optimizing the network and utilizing features more effectively. Experiments are conducted on the proposed L1-GCNN and existing methods using several metrics. The simulation results show relative improvements in student sentiment analysis for placement performance based on co-curricular activities, reducing the mean absolute error by 0.053, precision by 0.9, recall by 0.93, and accuracy by 0.89 compared to existing methods.
Downloads
References
[1] Z. Dai, "Analysis of college students' physical education learning effect and quality based on text data fusion," Adv. Continuous Discrete Models, vol. 25, no. 64, pp. 1–15, Mar. 2025, doi: 10.1186/s13662-025-03925-9.
[2] H. Liang and H. Liang, "Deep learning based multi-attribute evaluation for holistic student assessment in physical education," Sci. Rep., vol. 15, no. 1, pp. 1–17, May 2025, doi: 10.1038/s41598-025-02168-8.
[3] A. L. Hemdanou, M. L. Sefian, Y. Achtoun, and I. Tahiri, "Comparative analysis of feature selection and extraction methods for student performance prediction across different machine learning models," Comput. Educ. Artif. Intell., vol. 7, Art. no. 100301, Dec. 2024, doi: 10.1016/j.caeai.2024.100301.
[4] V. L. Williams, M. Haddad, K. A. Kelley, J. Li, and J. L. Rodis, "Evaluation of cocurricular learning and the influence of student choice," Am. J. Pharm. Educ., vol. 88, no. 8, Art. no. 101257, Sep. 2024, doi: 10.1016/j.ajpe.2024.101257.
[5] C. S. Moreno Cortez and J. Nevarez Montes, "Extracurricular arts: Effects on creativity and academics," J. Creativity, vol. 35, no. 1, Art. no. 100094, Apr. 2025, doi: 10.1016/j.yjoc.2025.100094.
[6] W. Strielkowski, V. Grebennikova, A. Lisovskiy, G. Rakhimova, and T. Vasileva, "AI-driven adaptive learning for sustainable educational transformation," Sustain. Dev., vol. 32, no. 2, pp. 1921–1947, Oct. 2024, doi: 10.1002/sd.3221.
[7] X. Li, "Student achievement prediction and auxiliary improvement method based on fuzzy decision support system," Discov. Artif. Intell., vol. 5, pp. 1–25, Apr. 2025, doi: 10.1007/s44163-025-00308-7.
[8] A. Olewnik, Y. Chang, and M. Su, "Co-curricular engagement among engineering undergrads: Do they have the time and motivation?" Int. J. STEM Educ., vol. 10, no. 1, pp. 1–20, Oct. 2023, doi: 10.1186/s40594-023-00410-1.
[9] E. Pürgstaller, J. Schmeling, L. Barkemeyer, M. Ullmann, and K. Koal, "Attitudes of physical education teachers and student teachers regarding digital media in physical education," Ger. J. Exerc. Sport Res., vol. 55, pp. 551–554, Apr. 2025, doi: 10.1007/s12662-025-01035-y.
[10] C. Weng, C. Chen, and X. Ai, "A pedagogical study on promoting students' deep learning through design-based learning," Int. J. Technol. Des. Educ., vol. 33, pp. 1653–1674, Nov. 2022, doi: 10.1007/s10798-022-09789-4.
[11] J. Yu and C. Qi, "Machine learning-based sentiment analysis in English literature: Using deep learning models to analyse emotional and thematic content in texts," IEEE Access, vol. 13, pp. 1–12, Apr. 2025, doi: 10.1109/ACCESS.2025.3553386.
[12] S. Leelaluk, T. Minematsu, C. Tang, Y. Taniguchi, F. Okubo, A. Shimada, and T. Yamashita, "Attention-based artificial neural network for student performance prediction based on learning activities," IEEE Access, vol. 12, pp. 100659–100675, Jul. 2024, doi: 10.1109/ACCESS.2024.3429554.
[13] Rahman, S. R., Islam, M. A., Akash, P. P., Parvin, M., Moon, N. N., & Nur, F. N., "Effects of co-curricular activities on students' academic performance by machine learning," Curr. Res. Behav. Sci., vol. 2, Art. no. 100057, Nov. 2021, doi: 10.1016/j.crbeha.2021.100057.
[14] D. Ileritürk, "Evaluation of extracurricular activities in education according to pre-school teacher candidates' views," Soc. Sci. Humanit. Open, vol. 8, no. 1, Art. no. 100524, Oct. 2023, doi: 10.1016/j.ssaho.2023.100524.
[15] H. V. Le, "Factors impeding university students' participation in English extracurricular activities: Time constraints and personal obstacles," Heliyon, vol. 10, no. 5, Art. no. e27332, Mar. 2024, doi: 10.1016/j.heliyon.2024.e27332.
[16] A. Milicevica, M. Despotovic-Zrakic, D. Stojanovic, M. Suvajzic, and A. Labus, "Academic performance indicators for the hackathon learning approach—The case of the blockchain hackathon," J. Innov. Knowl., vol. 9, no. 3, Art. no. 100501, Jun. 2024, doi: 10.1016/j.jik.2024.100501.
[17] E. Kalita, A. M. Alfarwan, H. El Aouifi, A. Kukkar, S. Hussain, T. Ali, and S. Gaftandzhieva, "Predicting student academic performance using Bi-LSTM: A deep learning framework with SHAP-based interpretability and statistical validation," Front. Educ., vol. 10, pp. 1–18, 2025, doi: 10.3389/feduc.2025.1581247.
[18] S. G. K. Salee, M. Asif, F.-E. Amin, and M. Imran, "Advancing aspect-based sentiment analysis in course evaluation: A multi-task learning framework with selective paraphrasing," IEEE Access, vol. 13, pp. 7764–7779, Jan. 2025, doi: 10.1109/ACCESS.2025.3527367.
[19] J. Pan, Z. Zhao, and D. Han, "Academic performance prediction using machine learning approaches: A survey," IEEE Trans. Learn. Technol., vol. 18, pp. 351–368, Jan. 2025, doi: 10.1109/TLT.2025.3554174.
[20] Y. Mamani-Coaquira and E. Villanueva, "A review on text sentiment analysis with machine learning and deep learning techniques," IEEE Access, vol. 12, pp. 193115–193130, Dec. 2024, doi: 10.1109/ACCESS.2024.3513321.
[21] I. S. Hueck, A. Guével, R. S. MacLeod, and K. Billiar, "Integration of co-curricular experiential learning in BME programs to increase student success," Biomed. Eng. Educ., vol. 5, pp. 189–202, Apr. 2025, doi: 10.1007/s43683-025-00183-9.
[22] R. Singh, S. K. Singh, and N. Mishra, "Factors influencing student learning performance and continuous use of artificial intelligence in online higher education," Discov. Educ., vol. 4, no. 292, pp. 1–18, Jun. 2025, doi: 10.1007/s44217-025-00728-8.
[23] D. Ç. Ertuğrul and S. Bitirim, "Job recommender systems: A systematic literature review, applications, open issues, and challenges," J. Big Data, vol. 12, no. 1, pp. 1–111, Jul. 2025, doi: 10.1186/s40537-025-01173-y.
[24] C. C. Thelma, E. V. Phiri, M. Morgan, and M. M. Gilbert, "The effect of co-curricular activities on learners' academic performance: A case of selected secondary schools in Lusaka District, Zambia," Int. J. Res., vol. 11, no. 8, pp. 243–265, Aug. 2024, doi: 10.5281/zenodo.13335567.
[25] A. W. O'Donnell, G. Redmond, A. A. Gardner, J. J. J. Wang, and A. Mooney, "Extracurricular activity participation, school belonging, and depressed mood: A test of the compensation hypothesis during adolescence," Appl. Dev. Sci., vol. 28, pp. 596–611, 2024, doi: 10.1080/10888691.2023.2260745.
[26] F. Lin, C. Li, R. W. Y. Lim, and Y. H. Lee, "Empower instructors with actionable insights: Mine and visualize student written feedback for instructors' reflection," Comput. Educ. Artif. Intell., vol. 8, Art. no. 100389, Jun. 2025, doi: 10.1016/j.caeai.2025.100389.
[27] S. Hooshangi, R. Buxton, and M. Ellis, "Integration of practical computing skills and co-curricular activities in the curriculum," in Proc. ACM Conf., Jul. 2022, pp. 61–67, doi: 10.1145/3502718.3524802.
[28] N. Wang and Q. Wang, "Modality-uncertainty-aware knowledge distillation framework for multimodal sentiment analysis," Complex Intell. Syst., vol. 12, 2026, doi: 10.1007/s40747-025-02135-w.
[29] W. Saidi, B. Satouri, and A. El Abderrahmani, "Optimal architecture for a sentiment analysis transformer with multihead attention and genetic crossover," Sci. Rep., vol. 15, Art. no. 37554, 2025, doi: 10.1038/s41598-025-22064-5.
[30] C. Yu and X. Yu, "Application of mobile learning system based on convolutional network technology in students' open teaching strategies," Sci. Rep., vol. 15, Art. no. 41646, 2025, doi: 10.1038/s41598-025-25532-0.
[31] K. S. Prasad, "Student placement data," Kaggle, 2020. [Online].
Available:https://www.kaggle.com/datasets/koshikasaiprasad/student-placement-data/data.
[32] S. Islam, "College student placement factors dataset," Kaggle, 2025. [Online].
Available:https://www.kaggle.com/datasets/sahilislam007/college-student-placement-factors-dataset.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 S. Johnbosco, Ravi Lourdusamy, Denis R, Peter Jose , P. Sathish, Mithun D'Souza
This work is licensed under a Creative Commons Attribution 4.0 International License.
