Authors : A. Hemanth Datta; A. Hrushi Jiyyan; G. Nagi Reddy; Dr. K. Sreekala; Manas Kumar Rath

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/ym8ezfb4

Scribd : https://tinyurl.com/yey2k7p8

DOI : https://doi.org/10.38124/ijisrt/26May1138

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Automated resume screening systems are widely used to manage large volumes of job applications; however, many existing approaches rely on rigid keyword matching or accuracy-focused machine learning models that fail to capture contextual skill relevance and may introduce algorithmic bias. This paper proposes a bias-aware automated resume screening framework that utilizes Natural Language Processing (NLP) techniques to analyze contextual relationships between candidate skills, experience, and job requirements. The system mitigates bias by identifying and neutralizing sensitive textual cues related to protected attributes such as gender or ethnicity. To evaluate robustness, screening outcomes are compared before and after the removal of noise and bias-related information. A Decision Stability Metric is introduced to measure the consistency of candidate rankings under controlled textual perturbations. Additionally, confidence calibration techniques are applied to ensure that the predicted probabilities accurately reflect the reliability of model decisions. The framework also improves transparency in automated hiring by enabling more consistent and interpretable candidate evaluation.

Keywords : Resume Screening, Natural Language Processing (NLP), Algorithmic Bias Detection, Decision Stability Analysis, Confidence Calibration, Explainable Artificial Intelligence.

References :

1. Y. Buolamwini and T. Gebru, “Auditing automated decision systems in high-stakes domains,” IEEE Trans. Technol. Soc., 2025.
2. A. Fabris et al., “Fairness and bias in algorithmic hiring,” ACM Computing Surveys, 2025.
3. M. M. A. M. Sony et al., “Bias in AI-driven HRM systems,” Journal of Business Research, 2025.
4. E. Ip et al., “Fair AI in hiring: Gender bias effects on applicant perceptions,” Human–Computer Interaction, 2025.
5. L. Floridi and M. Taddeo, “Trustworthy artificial intelligence: From principles to measurable guarantees,” IEEE Computer, vol. 58, no. 4, pp. 72–81, 2025.
6. R. Guidotti, A. Monreale, and F. Giannotti, “Post-hoc verification of black-box decision systems,” Knowledge- Based Systems, Elsevier, 2025.
7. J. García-González et al., “Explainable AI in recruitment systems,” Information Processing & Management, 2024.
8. C. Rigotti, “Fairness, AI & recruitment,” Information Systems Journal, 2024.
9. A. Mehrabi, F. Morstatter, and A. Galstyan, “Robustness and stability of machine learning under input perturbations,” IEEE Trans. Neural Netw. Learn. Syst., 2024.
10. K. Kallus and A. Zhou, “Decision stability and sensitivity analysis for machine learning classifiers,” IEEE Trans. Knowl. Data Eng., 2024.
11. Y. Chen et al., “Bias evaluation in automated hiring systems,” Knowledge-Based Systems, 2023.
12. P. Hiremath and S. Deshpande, “Resume classification using supervised learning,” International Journal of Information Management, 2023.
13. J. Lee and R. Singh, “Ethical risks of AI-based resume screening,” AI & Society, 2023.
14. C. Papakyriakopoulos et al., “Measuring bias in algorithmic hiring systems,” Data Mining and Knowledge Discovery, 2022.
15. T. Zhang et al., “Public perceptions of algorithmic hiring,” Technological Forecasting and Social Change, 2022.