@inproceedings{mor-lan-etal-2025-hebid,
title = "{H}eb{ID}: Detecting Social Identities in {H}ebrew-language Political Text",
author = "Mor-Lan, Guy and
Rivlin-Angert, Naama and
Kaplan, Yael R. and
Sheafer, Tamir and
Shenhav, Shaul R.",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.523/",
doi = "10.18653/v1/2025.findings-emnlp.523",
pages = "9850--9870",
ISBN = "979-8-89176-335-7",
abstract = "Political language is deeply intertwined with social identities. While social identities are often shaped by specific cultural contexts, existing NLP datasets are predominantly English-centric and focus on coarse-grained identity categories. We introduce HebID, the first multilabel Hebrew corpus for social identity detection. The corpus contains 5,536 sentences from Israeli politicians' Facebook posts (Dec 2018-Apr 2021), with each sentence manually annotated for twelve nuanced social identities (e.g., Rightist, Ultra-Orthodox, Socially-oriented) selected based on their salience in national survey data. We benchmark multilabel and single-label encoders alongside 2B-9B-parameter decoder LLMs, finding that Hebrew-tuned LLMs provide the best results (macro-$F_1$ = 0.74). We apply our classifier to politicians' Facebook posts and parliamentary speeches, evaluating differences in popularity, temporal trends, clustering patterns, and gender-related variations in identity expression. We utilize identity choices from a national public survey, comparing the identities portrayed in elite discourse with those prioritized by the public. HebID provides a comprehensive foundation for studying social identities in Hebrew and can serve as a model for similar research in other non-English political contexts"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mor-lan-etal-2025-hebid">
<titleInfo>
<title>HebID: Detecting Social Identities in Hebrew-language Political Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Mor-Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Rivlin-Angert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yael</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Kaplan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamir</namePart>
<namePart type="family">Sheafer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaul</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Shenhav</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>Findings of the Association for Computational Linguistics: EMNLP 2025</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Political language is deeply intertwined with social identities. While social identities are often shaped by specific cultural contexts, existing NLP datasets are predominantly English-centric and focus on coarse-grained identity categories. We introduce HebID, the first multilabel Hebrew corpus for social identity detection. The corpus contains 5,536 sentences from Israeli politicians’ Facebook posts (Dec 2018-Apr 2021), with each sentence manually annotated for twelve nuanced social identities (e.g., Rightist, Ultra-Orthodox, Socially-oriented) selected based on their salience in national survey data. We benchmark multilabel and single-label encoders alongside 2B-9B-parameter decoder LLMs, finding that Hebrew-tuned LLMs provide the best results (macro-F₁ = 0.74). We apply our classifier to politicians’ Facebook posts and parliamentary speeches, evaluating differences in popularity, temporal trends, clustering patterns, and gender-related variations in identity expression. We utilize identity choices from a national public survey, comparing the identities portrayed in elite discourse with those prioritized by the public. HebID provides a comprehensive foundation for studying social identities in Hebrew and can serve as a model for similar research in other non-English political contexts</abstract>
<identifier type="citekey">mor-lan-etal-2025-hebid</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.523</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.523/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>9850</start>
<end>9870</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HebID: Detecting Social Identities in Hebrew-language Political Text
%A Mor-Lan, Guy
%A Rivlin-Angert, Naama
%A Kaplan, Yael R.
%A Sheafer, Tamir
%A Shenhav, Shaul R.
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F mor-lan-etal-2025-hebid
%X Political language is deeply intertwined with social identities. While social identities are often shaped by specific cultural contexts, existing NLP datasets are predominantly English-centric and focus on coarse-grained identity categories. We introduce HebID, the first multilabel Hebrew corpus for social identity detection. The corpus contains 5,536 sentences from Israeli politicians’ Facebook posts (Dec 2018-Apr 2021), with each sentence manually annotated for twelve nuanced social identities (e.g., Rightist, Ultra-Orthodox, Socially-oriented) selected based on their salience in national survey data. We benchmark multilabel and single-label encoders alongside 2B-9B-parameter decoder LLMs, finding that Hebrew-tuned LLMs provide the best results (macro-F₁ = 0.74). We apply our classifier to politicians’ Facebook posts and parliamentary speeches, evaluating differences in popularity, temporal trends, clustering patterns, and gender-related variations in identity expression. We utilize identity choices from a national public survey, comparing the identities portrayed in elite discourse with those prioritized by the public. HebID provides a comprehensive foundation for studying social identities in Hebrew and can serve as a model for similar research in other non-English political contexts
%R 10.18653/v1/2025.findings-emnlp.523
%U https://aclanthology.org/2025.findings-emnlp.523/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.523
%P 9850-9870
Markdown (Informal)
[HebID: Detecting Social Identities in Hebrew-language Political Text](https://aclanthology.org/2025.findings-emnlp.523/) (Mor-Lan et al., Findings 2025)
ACL