A Diachronic Analysis of Human and Model Predictions on Audience Gender in How-to Guides

Nicola Fanton, Sidharth Ranjan, Titus Von Der Malsburg, Michael Roth


Abstract
We examine audience-specific how-to guides on wikiHow, in English, diachronically by comparing predictions from fine-tuned language models and human judgments. Using both early and revised versions, we quantitatively and qualitatively study how gender-specific features are identified over time. While language model performance remains relatively stable in terms of macro F1-scores, we observe an increased reliance on stereotypical tokens. Notably, both models and human raters tend to overpredict women as an audience, raising questions about bias in the evaluation of educational systems and resources.
Anthology ID:
2025.gebnlp-1.22
Volume:
Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
Month:
August
Year:
2025
Address:
Vienna, Austria
Editors:
Agnieszka Faleńska, Christine Basta, Marta Costa-jussà, Karolina Stańczak, Debora Nozza
Venues:
GeBNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
242–255
Language:
URL:
https://preview.aclanthology.org/landing_page/2025.gebnlp-1.22/
DOI:
10.18653/v1/2025.gebnlp-1.22
Bibkey:
Cite (ACL):
Nicola Fanton, Sidharth Ranjan, Titus Von Der Malsburg, and Michael Roth. 2025. A Diachronic Analysis of Human and Model Predictions on Audience Gender in How-to Guides. In Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 242–255, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
A Diachronic Analysis of Human and Model Predictions on Audience Gender in How-to Guides (Fanton et al., GeBNLP 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2025.gebnlp-1.22.pdf