@inproceedings{parappan-henao-2025-learning,
title = "Learning Subjective Label Distributions via Sociocultural Descriptors",
author = "Parappan, Mohammed Fayiz and
Henao, Ricardo",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1026/",
pages = "20333--20349",
ISBN = "979-8-89176-332-6",
abstract = "Subjectivity in NLP tasks, {\_}e.g.{\_}, toxicity classification, has emerged as a critical challenge precipitated by the increased deployment of NLP systems in content-sensitive domains. Conventional approaches aggregate annotator judgements (labels), ignoring minority perspectives, and overlooking the influence of the sociocultural context behind such annotations. We propose a framework where subjectivity in binary labels is modeled as an empirical distribution accounting for the variation in annotators through human values extracted from sociocultural descriptors using a language model. The framework also allows for downstream tasks such as population and sociocultural group-level majority label prediction. Experiments on three toxicity datasets covering human-chatbot conversations and social media posts annotated with diverse annotator pools demonstrate that our approach yields well-calibrated toxicity distribution predictions across binary toxicity labels, which are further used for majority label prediction across cultural subgroups, improving over existing methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parappan-henao-2025-learning">
<titleInfo>
<title>Learning Subjective Label Distributions via Sociocultural Descriptors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Fayiz</namePart>
<namePart type="family">Parappan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Subjectivity in NLP tasks, _e.g._, toxicity classification, has emerged as a critical challenge precipitated by the increased deployment of NLP systems in content-sensitive domains. Conventional approaches aggregate annotator judgements (labels), ignoring minority perspectives, and overlooking the influence of the sociocultural context behind such annotations. We propose a framework where subjectivity in binary labels is modeled as an empirical distribution accounting for the variation in annotators through human values extracted from sociocultural descriptors using a language model. The framework also allows for downstream tasks such as population and sociocultural group-level majority label prediction. Experiments on three toxicity datasets covering human-chatbot conversations and social media posts annotated with diverse annotator pools demonstrate that our approach yields well-calibrated toxicity distribution predictions across binary toxicity labels, which are further used for majority label prediction across cultural subgroups, improving over existing methods.</abstract>
<identifier type="citekey">parappan-henao-2025-learning</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1026/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>20333</start>
<end>20349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Subjective Label Distributions via Sociocultural Descriptors
%A Parappan, Mohammed Fayiz
%A Henao, Ricardo
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F parappan-henao-2025-learning
%X Subjectivity in NLP tasks, _e.g._, toxicity classification, has emerged as a critical challenge precipitated by the increased deployment of NLP systems in content-sensitive domains. Conventional approaches aggregate annotator judgements (labels), ignoring minority perspectives, and overlooking the influence of the sociocultural context behind such annotations. We propose a framework where subjectivity in binary labels is modeled as an empirical distribution accounting for the variation in annotators through human values extracted from sociocultural descriptors using a language model. The framework also allows for downstream tasks such as population and sociocultural group-level majority label prediction. Experiments on three toxicity datasets covering human-chatbot conversations and social media posts annotated with diverse annotator pools demonstrate that our approach yields well-calibrated toxicity distribution predictions across binary toxicity labels, which are further used for majority label prediction across cultural subgroups, improving over existing methods.
%U https://aclanthology.org/2025.emnlp-main.1026/
%P 20333-20349
Markdown (Informal)
[Learning Subjective Label Distributions via Sociocultural Descriptors](https://aclanthology.org/2025.emnlp-main.1026/) (Parappan & Henao, EMNLP 2025)
ACL