@inproceedings{wan-etal-2025-noise,
title = "From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis",
author = "Wan, Ruyuan and
Wang, Haonan and
Huang, Ting-Hao Kenneth and
Gao, Jie",
editor = "Blodgett, Su Lin and
Curry, Amanda Cercas and
Dev, Sunipa and
Li, Siyan and
Madaio, Michael and
Wang, Jack and
Wu, Sherry Tongshuang and
Xiao, Ziang and
Yang, Diyi",
booktitle = "Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.hcinlp-1.20/",
pages = "240--254",
ISBN = "979-8-89176-353-1",
abstract = "Subjective data annotation (SDA) plays an important role in many NLP tasks, including sentiment analysis, toxicity detection, and bias identification. Conventional SDA often treats annotator disagreement as noise, overlooking its potential to reveal deeper insights. In contrast, qualitative data analysis (QDA) explicitly engages with diverse positionalities and treats disagreement as a meaningful source of knowledge. In this position paper, we argue that human annotators are a key source of valuable interpretive insights into subjective data beyond surface-level descriptions. Through a comparative analysis of SDA and QDA methodologies, we examine similarities and differences in task nature (e.g., human{'}s role, analysis content, cost, and completion conditions) and practice (annotation schema, annotation workflow, annotator selection, and evaluation). Based on this comparison, we propose five practical recommendations for enabling SDA to capture richer insights. We demonstrate these recommendations in a reinforcement learning from human feedback (RLHF) case study and envision that our interdisciplinary perspective will offer new directions for the field."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2025-noise">
<titleInfo>
<title>From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haonan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Hao</namePart>
<namePart type="given">Kenneth</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Gao</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 Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="given">Cercas</namePart>
<namePart type="family">Curry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherry</namePart>
<namePart type="given">Tongshuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</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">979-8-89176-353-1</identifier>
</relatedItem>
<abstract>Subjective data annotation (SDA) plays an important role in many NLP tasks, including sentiment analysis, toxicity detection, and bias identification. Conventional SDA often treats annotator disagreement as noise, overlooking its potential to reveal deeper insights. In contrast, qualitative data analysis (QDA) explicitly engages with diverse positionalities and treats disagreement as a meaningful source of knowledge. In this position paper, we argue that human annotators are a key source of valuable interpretive insights into subjective data beyond surface-level descriptions. Through a comparative analysis of SDA and QDA methodologies, we examine similarities and differences in task nature (e.g., human’s role, analysis content, cost, and completion conditions) and practice (annotation schema, annotation workflow, annotator selection, and evaluation). Based on this comparison, we propose five practical recommendations for enabling SDA to capture richer insights. We demonstrate these recommendations in a reinforcement learning from human feedback (RLHF) case study and envision that our interdisciplinary perspective will offer new directions for the field.</abstract>
<identifier type="citekey">wan-etal-2025-noise</identifier>
<location>
<url>https://aclanthology.org/2025.hcinlp-1.20/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>240</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis
%A Wan, Ruyuan
%A Wang, Haonan
%A Huang, Ting-Hao Kenneth
%A Gao, Jie
%Y Blodgett, Su Lin
%Y Curry, Amanda Cercas
%Y Dev, Sunipa
%Y Li, Siyan
%Y Madaio, Michael
%Y Wang, Jack
%Y Wu, Sherry Tongshuang
%Y Xiao, Ziang
%Y Yang, Diyi
%S Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-353-1
%F wan-etal-2025-noise
%X Subjective data annotation (SDA) plays an important role in many NLP tasks, including sentiment analysis, toxicity detection, and bias identification. Conventional SDA often treats annotator disagreement as noise, overlooking its potential to reveal deeper insights. In contrast, qualitative data analysis (QDA) explicitly engages with diverse positionalities and treats disagreement as a meaningful source of knowledge. In this position paper, we argue that human annotators are a key source of valuable interpretive insights into subjective data beyond surface-level descriptions. Through a comparative analysis of SDA and QDA methodologies, we examine similarities and differences in task nature (e.g., human’s role, analysis content, cost, and completion conditions) and practice (annotation schema, annotation workflow, annotator selection, and evaluation). Based on this comparison, we propose five practical recommendations for enabling SDA to capture richer insights. We demonstrate these recommendations in a reinforcement learning from human feedback (RLHF) case study and envision that our interdisciplinary perspective will offer new directions for the field.
%U https://aclanthology.org/2025.hcinlp-1.20/
%P 240-254
Markdown (Informal)
[From Noise to Nuance: Enriching Subjective Data Annotation through Qualitative Analysis](https://aclanthology.org/2025.hcinlp-1.20/) (Wan et al., HCINLP 2025)
ACL