Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Innovation Information Technology and Application (JINITA)
Qisthi Alhazmi Hidayaturrohman
Graduate School of Science and Engineering, Saga University, Japan
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
A Reproducible Explainable NLP Workflow for Workplace Sexism Detection: Classification Performance, Rationale Faithfulness, and Sanity Checks Annisa Romadloni; Linda Perdana Wanti; Laura Sari; Muhammad Nur Faiz; Qisthi Alhazmi Hidayaturrohman
Journal of Innovation Information Technology and Application (JINITA) Vol 8 No 1 (2026): JINITA, June 2026
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/jinita.v8i1.3222

Abstract

Workplace sexism often appears as indirect, deniable language (e.g., patronizing compliments, competence-doubting questions), making automated detection and organizational response difficult. This study evaluates a transparent, explanation-ready NLP pipeline on the Sexist Workplace Statements (SWS) dataset (1,137 items) with its binary labels: certain sexism vs. ambiguous/neutral. Using the provided fixed stratified split (1,023 train; 114 test), we train a TF–IDF (word 1–2, character 3–5 n-grams) logistic regression baseline and report performance stability across five random seeds. To audit model evidence, sparse token rationales are extracted from linear feature contributions and quantify faithfulness with ERASER-style comprehensiveness (logit drop when rationales are removed) and sufficiency (logit change when only rationales are kept), benchmarked against random-token rationales. The baseline achieves 0.768 ± 0.006 accuracy and 0.759 ± 0.007 macro-F1, with errors concentrated in the ambiguous/neutral class. Faithfulness tests show that model-selected rationales substantially affect the sexism logit (comprehensiveness 1.335 ± 0.001), while remaining insufficient in isolation (|sufficiency| 1.075 ± 0.006). Sanity checks reveal modest sensitivity to gender-term swaps and reduced rationale overlap underweight randomization. Overall, results motivate cautious deployment: explanation-driven auditing can surface shortcut risks and clarify where binary labels blur neutral language and deniable sexism, pointing to future work on finer-grained annotation and human rationale collection.
Co-Authors Annisa Romadloni Laura Sari Linda Perdana Wanti Muhammad Nur Faiz