@inproceedings{kumar-oussalah-2026-aquacrisis,
title = "{A}qua{C}risis: A Multilingual Benchmark for Classifying Water-Utility Public Communication",
author = "Kumar, Vishal and
Oussalah, Mourad",
editor = "Schimanski, Tobias and
Usmanova, Aida and
Morio, Gaku and
Ni, Jingwei and
Dutia, Kalyan and
Vaghefi, Seyed Saeid and
Stammbach, Dominik and
Leippold, Markus",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change ({C}limate{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.climatenlp-1.18/",
pages = "246--281",
ISBN = "979-8-89176-465-1",
abstract = "Water utilities communicate both routine service information and time-sensitive public-risk guidance, yet multilingual NLP benchmarks for institution-authored infrastructure communication remain limited. We introduce AquaCrisis, a corpus of 20,000 text-bearing Facebook posts from 12 European water utilities, with a 1,500-post manually annotated gold standard. We formulate Task A as classification of a post{'}s main water-utility topic and Task B as classification of its primary communicative function, together with a coarser grouped Task B.1. We compare rule-based and supervised classifiers with four instruction-tuned LLMs on native-language and English-translated inputs. Supervised approaches achieve the highest point estimates on the fine-grained tasks: translated TF-IDF with logistic regression performs best on Task A, while translated multilingual sentence embeddings perform best on Task B. GPT-4o-mini achieves the highest point estimate on grouped Task B.1. Paired bootstrap analysis shows that translation effects are model- and setting-dependent: gains are clearest for the lexical TF-IDF classifier and selected Gemma 4 and GPT-4.1-mini conditions, while multilingual sentence embeddings, GPT-4o-mini, and Qwen 3.5 are comparatively stable across input representations. AquaCrisis provides a benchmark for multilingual water-utility communication spanning routine, educational, operational, and incident-related messaging, supporting communication monitoring, operational triage, and cross-lingual evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-oussalah-2026-aquacrisis">
<titleInfo>
<title>AquaCrisis: A Multilingual Benchmark for Classifying Water-Utility Public Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mourad</namePart>
<namePart type="family">Oussalah</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 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Usmanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Saeid</namePart>
<namePart type="family">Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</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">979-8-89176-465-1</identifier>
</relatedItem>
<abstract>Water utilities communicate both routine service information and time-sensitive public-risk guidance, yet multilingual NLP benchmarks for institution-authored infrastructure communication remain limited. We introduce AquaCrisis, a corpus of 20,000 text-bearing Facebook posts from 12 European water utilities, with a 1,500-post manually annotated gold standard. We formulate Task A as classification of a post’s main water-utility topic and Task B as classification of its primary communicative function, together with a coarser grouped Task B.1. We compare rule-based and supervised classifiers with four instruction-tuned LLMs on native-language and English-translated inputs. Supervised approaches achieve the highest point estimates on the fine-grained tasks: translated TF-IDF with logistic regression performs best on Task A, while translated multilingual sentence embeddings perform best on Task B. GPT-4o-mini achieves the highest point estimate on grouped Task B.1. Paired bootstrap analysis shows that translation effects are model- and setting-dependent: gains are clearest for the lexical TF-IDF classifier and selected Gemma 4 and GPT-4.1-mini conditions, while multilingual sentence embeddings, GPT-4o-mini, and Qwen 3.5 are comparatively stable across input representations. AquaCrisis provides a benchmark for multilingual water-utility communication spanning routine, educational, operational, and incident-related messaging, supporting communication monitoring, operational triage, and cross-lingual evaluation.</abstract>
<identifier type="citekey">kumar-oussalah-2026-aquacrisis</identifier>
<location>
<url>https://aclanthology.org/2026.climatenlp-1.18/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>246</start>
<end>281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AquaCrisis: A Multilingual Benchmark for Classifying Water-Utility Public Communication
%A Kumar, Vishal
%A Oussalah, Mourad
%Y Schimanski, Tobias
%Y Usmanova, Aida
%Y Morio, Gaku
%Y Ni, Jingwei
%Y Dutia, Kalyan
%Y Vaghefi, Seyed Saeid
%Y Stammbach, Dominik
%Y Leippold, Markus
%S Proceedings of the 3rd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-465-1
%F kumar-oussalah-2026-aquacrisis
%X Water utilities communicate both routine service information and time-sensitive public-risk guidance, yet multilingual NLP benchmarks for institution-authored infrastructure communication remain limited. We introduce AquaCrisis, a corpus of 20,000 text-bearing Facebook posts from 12 European water utilities, with a 1,500-post manually annotated gold standard. We formulate Task A as classification of a post’s main water-utility topic and Task B as classification of its primary communicative function, together with a coarser grouped Task B.1. We compare rule-based and supervised classifiers with four instruction-tuned LLMs on native-language and English-translated inputs. Supervised approaches achieve the highest point estimates on the fine-grained tasks: translated TF-IDF with logistic regression performs best on Task A, while translated multilingual sentence embeddings perform best on Task B. GPT-4o-mini achieves the highest point estimate on grouped Task B.1. Paired bootstrap analysis shows that translation effects are model- and setting-dependent: gains are clearest for the lexical TF-IDF classifier and selected Gemma 4 and GPT-4.1-mini conditions, while multilingual sentence embeddings, GPT-4o-mini, and Qwen 3.5 are comparatively stable across input representations. AquaCrisis provides a benchmark for multilingual water-utility communication spanning routine, educational, operational, and incident-related messaging, supporting communication monitoring, operational triage, and cross-lingual evaluation.
%U https://aclanthology.org/2026.climatenlp-1.18/
%P 246-281
Markdown (Informal)
[AquaCrisis: A Multilingual Benchmark for Classifying Water-Utility Public Communication](https://aclanthology.org/2026.climatenlp-1.18/) (Kumar & Oussalah, ClimateNLP 2026)
ACL