@inproceedings{aupi-etal-2025-wonbias,
    title = "{W}o{NB}ias: A Dataset for Classifying Bias {\&} Prejudice Against Women in {B}engali Text",
    author = "Aupi, Md. Raisul Islam  and
      Tafannum, Nishat  and
      Rahman, Md. Shahidur  and
      Hassan, Kh Mahmudul  and
      Rahman, Naimur",
    editor = "Fale{\'n}ska, Agnieszka  and
      Basta, Christine  and
      Costa-juss{\`a}, Marta  and
      Sta{\'n}czak, Karolina  and
      Nozza, Debora",
    booktitle = "Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.gebnlp-1.10/",
    doi = "10.18653/v1/2025.gebnlp-1.10",
    pages = "105--110",
    ISBN = "979-8-89176-277-0",
    abstract = "This paper presents WoNBias, a curated Bengali dataset to identify gender-based biases, stereotypes, and harmful language directed at women. It merges digital sources- social media, blogs, news- with offline tactics comprising surveys and focus groups, alongside some existing corpora to compile a total of 31,484 entries (10,656 negative; 10,170 positive; 10,658 neutral). WoNBias reflects the sociocultural subtleties of bias in both Bengali digital and offline conversations. By bridging online and offline biased contexts, the dataset supports content moderation, policy interventions, and equitable NLP research for Bengali, a low-resource language critically underserved by existing tools. WoNBias aims to combat systemic gender discrimination against women on digital platforms, empowering researchers and practitioners to combat harmful narratives in Bengali-speaking communities."
}