@inproceedings{belay-etal-2025-culemo,
title = "{CULEMO}: Cultural Lenses on Emotion - Benchmarking {LLM}s for Cross-Cultural Emotion Understanding",
author = "Belay, Tadesse Destaw and
Ahmed, Ahmed Haj and
Grissom II, Alvin and
Ameer, Iqra and
Sidorov, Grigori and
Kolesnikova, Olga and
Yimam, Seid Muhie",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.925/",
doi = "10.18653/v1/2025.acl-long.925",
pages = "18894--18909",
ISBN = "979-8-89176-251-0",
abstract = "NLP research has increasingly focused on subjective tasks such as emotion analysis. However, existing emotion benchmarks suffer fromtwo major shortcomings: (1) they largely rely on keyword-based emotion recognition, overlooking crucial cultural dimensions required fordeeper emotion understanding, and (2) many are created by translating English-annotated data into other languages, leading to potentially unreliable evaluation. To address these issues, we introduce Cultural Lenses on Emotion (CuLEmo), the first benchmark designedto evaluate culture-aware emotion prediction across six languages: Amharic, Arabic, English, German, Hindi, and Spanish. CuLEmocomprises 400 crafted questions per language, each requiring nuanced cultural reasoning and understanding. We use this benchmark to evaluate several state-of-the-art LLMs on culture-aware emotion prediction and sentiment analysis tasks. Our findings reveal that (1) emotion conceptualizations vary significantly across languages and cultures, (2) LLMs performance likewise varies by language and cultural context, and (3) prompting in English with explicit country context often outperforms in-language prompts for culture-aware emotion and sentiment understanding. The dataset and evaluation code is available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belay-etal-2025-culemo">
<titleInfo>
<title>CULEMO: Cultural Lenses on Emotion - Benchmarking LLMs for Cross-Cultural Emotion Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="given">Destaw</namePart>
<namePart type="family">Belay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Haj</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alvin</namePart>
<namePart type="family">Grissom II</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iqra</namePart>
<namePart type="family">Ameer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kolesnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seid</namePart>
<namePart type="given">Muhie</namePart>
<namePart type="family">Yimam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>NLP research has increasingly focused on subjective tasks such as emotion analysis. However, existing emotion benchmarks suffer fromtwo major shortcomings: (1) they largely rely on keyword-based emotion recognition, overlooking crucial cultural dimensions required fordeeper emotion understanding, and (2) many are created by translating English-annotated data into other languages, leading to potentially unreliable evaluation. To address these issues, we introduce Cultural Lenses on Emotion (CuLEmo), the first benchmark designedto evaluate culture-aware emotion prediction across six languages: Amharic, Arabic, English, German, Hindi, and Spanish. CuLEmocomprises 400 crafted questions per language, each requiring nuanced cultural reasoning and understanding. We use this benchmark to evaluate several state-of-the-art LLMs on culture-aware emotion prediction and sentiment analysis tasks. Our findings reveal that (1) emotion conceptualizations vary significantly across languages and cultures, (2) LLMs performance likewise varies by language and cultural context, and (3) prompting in English with explicit country context often outperforms in-language prompts for culture-aware emotion and sentiment understanding. The dataset and evaluation code is available.</abstract>
<identifier type="citekey">belay-etal-2025-culemo</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.925</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.925/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18894</start>
<end>18909</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CULEMO: Cultural Lenses on Emotion - Benchmarking LLMs for Cross-Cultural Emotion Understanding
%A Belay, Tadesse Destaw
%A Ahmed, Ahmed Haj
%A Grissom II, Alvin
%A Ameer, Iqra
%A Sidorov, Grigori
%A Kolesnikova, Olga
%A Yimam, Seid Muhie
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F belay-etal-2025-culemo
%X NLP research has increasingly focused on subjective tasks such as emotion analysis. However, existing emotion benchmarks suffer fromtwo major shortcomings: (1) they largely rely on keyword-based emotion recognition, overlooking crucial cultural dimensions required fordeeper emotion understanding, and (2) many are created by translating English-annotated data into other languages, leading to potentially unreliable evaluation. To address these issues, we introduce Cultural Lenses on Emotion (CuLEmo), the first benchmark designedto evaluate culture-aware emotion prediction across six languages: Amharic, Arabic, English, German, Hindi, and Spanish. CuLEmocomprises 400 crafted questions per language, each requiring nuanced cultural reasoning and understanding. We use this benchmark to evaluate several state-of-the-art LLMs on culture-aware emotion prediction and sentiment analysis tasks. Our findings reveal that (1) emotion conceptualizations vary significantly across languages and cultures, (2) LLMs performance likewise varies by language and cultural context, and (3) prompting in English with explicit country context often outperforms in-language prompts for culture-aware emotion and sentiment understanding. The dataset and evaluation code is available.
%R 10.18653/v1/2025.acl-long.925
%U https://aclanthology.org/2025.acl-long.925/
%U https://doi.org/10.18653/v1/2025.acl-long.925
%P 18894-18909
Markdown (Informal)
[CULEMO: Cultural Lenses on Emotion - Benchmarking LLMs for Cross-Cultural Emotion Understanding](https://aclanthology.org/2025.acl-long.925/) (Belay et al., ACL 2025)
ACL