Classification and Interpretability of Employee Burnout Using Linear Discriminant Analysis
DOI:
https://doi.org/10.62712/juktisi.v4i3.811Kata Kunci:
Employee Burnout, Linear Discriminant Analysis, Machine Learning, , Interpretabilitas Model, Kesehatan Mental KerjaAbstrak
Employee burnout merupakan permasalahan serius dalam organisasi modern karena berdampak langsung pada kesejahteraan psikologis karyawan, produktivitas kerja, serta keberlanjutan kinerja organisasi. Proses identifikasi burnout di banyak organisasi masih bersifat subjektif dan kurang terintegrasi dengan pendekatan analitik yang transparan. Penelitian ini bertujuan untuk mengembangkan model klasifikasi risiko burnout karyawan yang tidak hanya memiliki tingkat akurasi tinggi, tetapi juga mudah diinterpretasikan oleh praktisi non-teknis. Metode Linear Discriminant Analysis (LDA) dipilih karena kemampuannya dalam memisahkan kelas secara optimal sekaligus menyediakan koefisien diskriminan yang dapat digunakan untuk analisis faktor dominan. Dataset yang digunakan merupakan data sekunder Mental Health in Workplace Survey dengan 3.000 data karyawan dan 15 variabel terkait kondisi kerja, faktor psikososial, serta karakteristik individu. Model dilatih menggunakan 80% data dan diuji pada 20% data sisanya. Hasil pengujian menunjukkan bahwa model LDA mencapai akurasi sebesar 96,17%, dengan nilai recall 100%, precision 89,50%, F1-score 94,46%, serta AUC sebesar 0,9988. Analisis interpretabilitas menunjukkan bahwa tingkat burnout individu, peran jabatan, serta faktor keseimbangan kerja–hidup dan pengembangan karier merupakan variabel yang paling berpengaruh terhadap klasifikasi risiko burnout. Temuan ini menegaskan bahwa LDA merupakan pendekatan yang efektif dan interpretabel untuk mendukung deteksi dini burnout serta perancangan intervensi berbasis data di lingkungan kerja.
Unduhan
Referensi
M. S and J. Krishnan, “Analyzing Employee Attrition Drivers: The Impact of Burnout Through Predictive Models,” Int. J. Sci. Technol., Jun. 2025, doi: 10.71097/ijsat.v16.i2.6248.
A. Sajeena, “Employee Burnout Prediction Using Data Sceince,” INTERANTIONAL J. Sci. Res. Eng. Manag., Jan. 2025, doi: 10.55041/ijsrem41241.
G. Fehér et al., “Mental issues, internet addiction and quality of life predict burnout among Hungarian teachers: a machine learning analysis,” BMC Public Health, vol. 24, Aug. 2024, doi: 10.1186/s12889-024-19797-9.
Y. Shoman, S. Marca, R. Bianchi, L. Godderis, H. Van Der Molen, and G. Canu, “Psychometric properties of burnout measures: a systematic review,” Epidemiol. Psychiatr. Sci., vol. 30, Jan. 2021, doi: 10.1017/s2045796020001134.
P. Zhernova, Y. Bodyanskiy, B. Yatsenko, and I. Zavgorodnii, “Detection and Prevention of Professional Burnout Using Machine Learning Methods,” 2020 IEEE 15th Int. Conf. Adv. Trends Radioelectron. Telecommun. Comput. Eng. TCSET, pp. 218–221, Feb. 2020, doi: 10.1109/tcset49122.2020.235426.
C. Thrush, M. Gathright, T. Atkinson, E. Messias, and B. Guise, “Psychometric Properties of the Copenhagen Burnout Inventory in an Academic Healthcare Institution Sample in the U.S.,” Eval. Health Prof., vol. 44, pp. 400–405, Jun. 2020, doi: 10.1177/0163278720934165.
S. Tyagi, A. Tomar, and M. Mohit, “Prediction of Mental Burnout Using Machine Learning,” Int. J. Sci. Res. Eng. Manag., Nov. 2025, doi: 10.55041/ijsrem53497.
M. Grządzielewska, “Using Machine Learning in Burnout Prediction: A Survey,” Child Adolesc. Soc. Work J., vol. 38, pp. 175–180, Jan. 2021, doi: 10.1007/s10560-020-00733-w.
M. Van Zyl-Cillié, J. Bührmann, A. Blignaut, D. Demirtas, and S. Coetzee, “A machine learning model to predict the risk factors causing feelings of burnout and emotional exhaustion amongst nursing staff in South Africa,” BMC Health Serv. Res., vol. 24, 2024, doi: 10.1186/s12913-024-12184-5.
A. Hernandez, E. Albina, and R. Perez, “Development of Occupational Burnout Prediction Models Using Machine Learning Techniques and Maslach Burnout Inventory,” 2024 IEEE 15th Control Syst. Grad. Res. Colloq. ICSGRC, pp. 47–51, Aug. 2024, doi: 10.1109/icsgrc62081.2024.10690950.
S. Hladiholov and O. Mokin, “Comparative Analysis of Machine Learning Models for Predicting Employee Burnout Problem,” Visnyk Vinnytsia Politech. Inst., 2023, doi: 10.31649/1997-9266-2023-170-5-25-31.
A. Alatrany, W. Khan, A. Hussain, H. Kolivand, and D. Al-Jumeily, “An explainable machine learning approach for Alzheimer’s disease classification,” Sci. Rep., vol. 14, 2024, doi: 10.1038/s41598-024-51985-w.
T. Kaluarachchi, A. Reis, and S. Nanayakkara, “A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning,” Sensors, vol. 21, 2021, doi: 10.3390/s21072514.
J. Van Der Donckt, E. Deprost, N. Vandenbussche, M. Rademaker, G. Vandewiele, and S. Van Hoecke, “Do not sleep on traditional machine learning: Simple and interpretable techniques are competitive to deep learning for sleep scoring,” Biomed. Signal Process. Control, vol. 81, p. 104429, 2022, doi: 10.1016/j.bspc.2022.104429.
J. Park, J. Ahn, and Y. Jeon, “Sparse functional linear discriminant analysis,” Biometrika, Nov. 2020, doi: 10.1093/biomet/asaa107.
H. Zhou, “Linear discriminant analysis,” Nat. Rev. Methods Primer, vol. 4, Jan. 2020, doi: 10.1038/s43586-024-00357-9.
J. Wen et al., “Robust Sparse Linear Discriminant Analysis,” IEEE Trans. Circuits Syst. Video Technol., vol. 29, pp. 390–403, Feb. 2019, doi: 10.1109/tcsvt.2018.2799214.
K. Sakakibara, A. Shimazu, H. Toyama, and W. Schaufeli, “Validation of the Japanese Version of the Burnout Assessment Tool,” Front. Psychol., vol. 11, Aug. 2020, doi: 10.3389/fpsyg.2020.01819.
H. Sun, T. Zhang, X. Wang, C. Wang, M. Zhang, and H. Song, “The occupational burnout among medical staff with high workloads after the COVID-19 and its association with anxiety and depression,” Front. Public Health, vol. 11, Oct. 2023, doi: 10.3389/fpubh.2023.1270634.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Dwi Robiul Rochmawati, Muhammad Al Adib, Diyo Mollana Fazri, Bill Raj, Romi Antoni, Rahmad Santoso, Wahyu Saptha Negoro
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
