@inproceedings{hamdane-etal-2026-pluralistic,
title = "Pluralistic Annotation of Cultural Weaponization on {W}ikipedia: A Multi-Annotator Case Study across {U}kraine and {A}rmenia",
author = "Hamdane, Camil and
Perekhoda, Hanna and
Boros, Emanuela and
Prezioso, Stefanie and
Tamrazyan, Hamest",
editor = "Xu, Shanshan and
T.Y.S.S., Santosh and
Kurniawan, Kemal and
Peng, Siyao and
Wallbridge, Sarenne and
Koto, Fajri and
Dziri, Nouha and
Plank, Barbara",
booktitle = "Proceedings of the First Workshop on Pluralistic {AI} {NLP}: Diversity-aware, Sociotechnical, Responsible Alignment ({PANDORA} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.pandora-1.5/",
pages = "105--120",
ISBN = "979-8-89176-484-2",
abstract = "Detecting the weaponization of cultural heritage on Wikipedia is not a straightforward classification task. Whether an edit manipulates a historical or cultural narrative often depends on context, interpretation, and the perspectives of those assessing it. We examine this challenge through a study of 400 English-language Wikipedia edits concerning Ukraine and Armenia. Three expert annotators independently classified each edit as Potentially Manipulative, Not Problematic, or Ambiguous, before resolving disagreements through structured discussion. We also compared their judgments with those of a large language model. More than one-third of the edits prompted disagreement, and discussion frequently produced decisions that could not be recovered through majority voting alone. The model aligned more closely with the experts' deliberated decisions than with their initial majority votes, demonstrating that the construction of ``gold'' labels can substantially affect how model performance is understood. Our findings also show that Ambiguous captures genuine evidential and interpretive uncertainty rather than annotation failure. We argue that culturally sensitive annotation should preserve disagreement, treat ambiguity as a meaningful outcome, and use deliberation, not mechanical aggregation, to construct reference labels."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamdane-etal-2026-pluralistic">
<titleInfo>
<title>Pluralistic Annotation of Cultural Weaponization on Wikipedia: A Multi-Annotator Case Study across Ukraine and Armenia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Camil</namePart>
<namePart type="family">Hamdane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Perekhoda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emanuela</namePart>
<namePart type="family">Boros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefanie</namePart>
<namePart type="family">Prezioso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamest</namePart>
<namePart type="family">Tamrazyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pluralistic AI NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kemal</namePart>
<namePart type="family">Kurniawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarenne</namePart>
<namePart type="family">Wallbridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-484-2</identifier>
</relatedItem>
<abstract>Detecting the weaponization of cultural heritage on Wikipedia is not a straightforward classification task. Whether an edit manipulates a historical or cultural narrative often depends on context, interpretation, and the perspectives of those assessing it. We examine this challenge through a study of 400 English-language Wikipedia edits concerning Ukraine and Armenia. Three expert annotators independently classified each edit as Potentially Manipulative, Not Problematic, or Ambiguous, before resolving disagreements through structured discussion. We also compared their judgments with those of a large language model. More than one-third of the edits prompted disagreement, and discussion frequently produced decisions that could not be recovered through majority voting alone. The model aligned more closely with the experts’ deliberated decisions than with their initial majority votes, demonstrating that the construction of “gold” labels can substantially affect how model performance is understood. Our findings also show that Ambiguous captures genuine evidential and interpretive uncertainty rather than annotation failure. We argue that culturally sensitive annotation should preserve disagreement, treat ambiguity as a meaningful outcome, and use deliberation, not mechanical aggregation, to construct reference labels.</abstract>
<identifier type="citekey">hamdane-etal-2026-pluralistic</identifier>
<location>
<url>https://aclanthology.org/2026.pandora-1.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>105</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pluralistic Annotation of Cultural Weaponization on Wikipedia: A Multi-Annotator Case Study across Ukraine and Armenia
%A Hamdane, Camil
%A Perekhoda, Hanna
%A Boros, Emanuela
%A Prezioso, Stefanie
%A Tamrazyan, Hamest
%Y Xu, Shanshan
%Y T.Y.S.S., Santosh
%Y Kurniawan, Kemal
%Y Peng, Siyao
%Y Wallbridge, Sarenne
%Y Koto, Fajri
%Y Dziri, Nouha
%Y Plank, Barbara
%S Proceedings of the First Workshop on Pluralistic AI NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-484-2
%F hamdane-etal-2026-pluralistic
%X Detecting the weaponization of cultural heritage on Wikipedia is not a straightforward classification task. Whether an edit manipulates a historical or cultural narrative often depends on context, interpretation, and the perspectives of those assessing it. We examine this challenge through a study of 400 English-language Wikipedia edits concerning Ukraine and Armenia. Three expert annotators independently classified each edit as Potentially Manipulative, Not Problematic, or Ambiguous, before resolving disagreements through structured discussion. We also compared their judgments with those of a large language model. More than one-third of the edits prompted disagreement, and discussion frequently produced decisions that could not be recovered through majority voting alone. The model aligned more closely with the experts’ deliberated decisions than with their initial majority votes, demonstrating that the construction of “gold” labels can substantially affect how model performance is understood. Our findings also show that Ambiguous captures genuine evidential and interpretive uncertainty rather than annotation failure. We argue that culturally sensitive annotation should preserve disagreement, treat ambiguity as a meaningful outcome, and use deliberation, not mechanical aggregation, to construct reference labels.
%U https://aclanthology.org/2026.pandora-1.5/
%P 105-120
Markdown (Informal)
[Pluralistic Annotation of Cultural Weaponization on Wikipedia: A Multi-Annotator Case Study across Ukraine and Armenia](https://aclanthology.org/2026.pandora-1.5/) (Hamdane et al., PANDORA 2026)
ACL