Abstract

Employees’ job satisfaction plays a significant role in enhancing organizational productivity and promoting industrial harmony. In recent years, the assessment of job satisfaction has attracted considerable attention from researchers. Conventional evaluation methods, such as regression and other statistical models, often fail to adequately capture the complex and nonlinear interactions among the determinants of job satisfaction. Advances in machine learning have introduced intelligent techniques capable of modeling such complexities in human resource phenomena. However, existing studies are limited in the integration of machine learning outputs with practical human resource evaluation frameworks. This study proposes an intelligent framework based on a Multilayer Perceptron Artificial Neural Network (MLP-ANN) for the assessment of employees’ job satisfaction. A total of twenty-two job-related attributes were obtained from structured questionnaires administered to employees of the Ministry of Science and Technology, Akwa Ibom State, Nigeria, yielding 450 data samples. The dataset was partitioned into training, testing, and validation sets using an 8:1:1 ratio. The MLP-ANN model, trained with a learning rate of 0.01, achieved an accuracy of 97.7% and a precision of 95.3% on the test dataset. The findings indicate that major factors influencing job satisfaction include satisfaction with salary, recognition by superiors, fairness in promotion policies, rewards for dedication, and opportunities for career advancement. The results demonstrate the suitability of neural network–based framework as a decision-support tool for enhancing industrial productivity and enabling proactive human resource management.

References

• Tria, J. Z. (2023). Job satisfaction among educators: A systematic review. European Journal of Educational Research, 12(2), e2310
• Abuhashesh, M., Al Dmour, R., and Masa’deh, R. (2019). Factors affecting employees’ job satisfaction. Journal of Social Sciences, 8(2): 1–14.
• Chavez, H., Chavez-Arias, B., Contreras-Rosas, S., Alvarez Rodriguez, J. M., and Raymundo, C. (2023). Artificial neural network model to predict student performance using nonpersonal information. Frontiers in Education, 8, 1106679.
• Phuong, T. T., and Le Ha, N. T. (2022). Knowledge management, employee satisfaction, employee loyalty and job performance: A proposed study. International Journal of Information, Business and Management, 14(1):1–16.
• Udoh, S. S., Asuquo, D. E., & Inyang, U. G. (2018). Adaptive neuro fuzzy model for oil pipeline monitoring in a cluster based sensor network. World Journal of Applied Science and Technology, 10(1B): 184–190.
• Udoh, S. S., Umoh, U. A., Umoh, M. E., and Udo, M. E. (2019). Diagnosis of prostate cancer using soft computing paradigms. Global Journal of Computer Science and Technology: Neural and Artificial Intelligence, 19(2): 19–26.
• Udoh, S. S., Inyang, U. G., Umoh, U. A., George, U. D., Etuk, U. R., Akpan, T. B., and Bassey, E. M. (2023). Deep learning based neural network modelling for cassava yield prediction. International Journal of Scientific and Engineering Research, 14(8): 1–18.
• Udoh, S. S., Ekong, K. C., Usip, P. U., Asuquo, D. E., Moffat, I. U., George, U. D., and Umoh, U. A. (2024). Intelligent discrete event system specification for monitoring cyber-attacks in airports. International Journal of Scientific Research and Development, 3(8): 63–72.
• Udoh, S. S., George, U. D., & Etuk, U. R. (2023). Cassava yield forecasting using artificial neural network. In Contemporary Discourse on Nigeria’s Economic Profile: A Festschrift in Honour of Prof. Nyaudoh U. Ndaeyo (pp. 667–679). Uyo: University of Uyo Press.
• León, H. C. R., Navarro, E. R., Meléndez, L. V., Salazar, T. D. R. M., Yuncor, N. R. C., and María, E. M. (2021). Job satisfaction factors in secondary school teachers: Public and private institutions in a Peruvian region. Cypriot Journal of Educational Sciences, 16(6):3317–3328.
• Özkan, U. B., and Akgenç (2022). Teachers’ job satisfaction: Multilevel analyses of teacher, school and principal effects. Forum for International Research in Education, 7(3):1–23.
• Hasyim, H., and Bakri, M. (2024). Pay and incentive inequality: A systematic review of their effects on work motivation. Paradoks: Jurnal Ilmu Ekonomi, 7(1): 69–84.
• Abiona, B. G., Adenuga, O. O., Adeosun, K. G., Fapojuwo, O. E., and Roseje, T. O. (2023). Assessment of job satisfaction among employees of Animal Care Services Konsult Limited, Ogun State, Nigeria. FUDMA Journal of Sciences, 7(3): 257–265.
• Levi, N. N. (2023). Evaluation of employees’ job satisfaction in three private organizations in Edo State, Nigeria. International Journal of Management and Entrepreneurship Research, 5(11):814–830.
• Tharu, R. P. (2019). Multiple regression model for job satisfaction of employees in saving and cooperative organizations. International Journal of Statistics and Applied Mathematics, 4(4): 43–49.
• Obeng, H. A., Arhinful, R., Mensah, L., and Owusu Sarfo, J. S. (2024). Influence of knowledge management cycle on job satisfaction and organizational culture considering employee engagement. Sustainability, 16(20): 8728.
• Asoba, S. N., and Mefi, N. P. (2021). Monitoring and management mechanisms on stress in higher education institutions in Eastern Cape Province, South Africa: A critical review. Academy of Entrepreneurship Journal, 27(2): 1–11.
• Oleabhiele, E. J. (2025). Impacts and benefits of quality work life programmes in Nigerian manufacturing companies. International Journal of Research and Innovation in Social Science, 9(16): 1–15.
• Sunn, C. Y., Peng, C. N., Qing, S. Z., Norhayati, W., Othman, B. W., Yusop, Y. M., and Anuar, M. (2024). Factors affecting job dissatisfaction in Asia: A systematic review. International Journal of Academic Research in Business and Social Sciences, 14(11): 1112–1127.
• Statista Research Department (2024). APAC: Employee job satisfaction by country 2024. Statista Report, Statista Inc., Germany.
• Udoh, S. S., Akinyokun, O. C., Inyang, U. G., Olabode, O., and Iwasokun, G. B. (2017). Discrete event based hybrid framework for petroleum pipeline activity classification. Journal of Artificial Intelligence Research, 6(2):39–50.
• Udoh, S. S., Obot, O. U., George, U. D., and Isong, E. B. (2012). Modified (s, S) inventory model using artificial neural network. International Journal of Scientific and Engineering Research, 3(5): 992–995.
• Arqawi, S., Rumman, M., Zitawi, E., Abunasser, B., and Abu-Naser, S. A. (2022). Predicting employee attrition and performance using deep learning. Journal of Theoretical and Applied Information Technology, 100(21): 6526–6536.
• Raza, A., Munir, K., Almutairi, M. I., Younas, F., and Fareed, M. S. (2022). Predicting employee attrition using machine learning approaches. Applied Sciences, 12(13), 6424.
• Al-Darraji, S., Honi, D. G., Fallucchi, F., Abdulsada, A. I., Guliano, R., and Abdulmalik, H. A. (2021). Employee attrition prediction using deep neural networks. Computers, 10(11): 141.
• Bajhzer, R. M., Alsenani, Y., Jambi, S., and Hasanin, T. (2026). ANN based employee performance prediction: A comparative analysis of optimization techniques. International Journal of Advanced Computer Science and Applications, 17(3): 1098–1105.
• Udoh, S. S., Usip, P. U., George, U. D., & Akpan, I. E. (2024). Adaptive neuro fuzzy based depression detection model for students in tertiary education. In Applied Machine Learning and Data Analytics (pp. 156–167). Cham: Springer.