@inproceedings{sucu-etal-2025-exploiting,
title = "Exploiting contextual information to improve stance detection in informal political discourse with {LLM}s",
author = "Sucu, Arman Engin and
Zhou, Yixiang and
Nascimento, Mario A. and
Mullen, Tony",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.86/",
doi = "10.18653/v1/2025.acl-srw.86",
pages = "1097--1110",
ISBN = "979-8-89176-254-1",
abstract = "This study investigates the use of Large Language Models (LLMs) for political stance detection in informal online discourse, where language is often sarcastic, ambiguous, and context-dependent. We explore whether providing contextual information, specifically user profile summaries derived from historical posts, can improve classification accuracy. Using a real-world political forum dataset, we generate structured profiles that summarize users' ideological leaning, recurring topics, and linguistic patterns. We evaluate seven state-of-the-art LLMs across baseline and context-enriched setups through a comprehensive cross-model evaluation. Our findings show that contextual prompts significantly boost accuracy, with improvements ranging from +17.5{\%} to +38.5{\%}, achieving up to 74{\%} accuracy that surpasses previous approaches. We also analyze how profile size and post selection strategies affect performance, showing that strategically chosen political content yields better results than larger, randomly selected contexts. These findings underscore the value of incorporating user-level context to enhance LLM performance in nuanced political classification tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sucu-etal-2025-exploiting">
<titleInfo>
<title>Exploiting contextual information to improve stance detection in informal political discourse with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="given">Engin</namePart>
<namePart type="family">Sucu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixiang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Nascimento</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="family">Mullen</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</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">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>This study investigates the use of Large Language Models (LLMs) for political stance detection in informal online discourse, where language is often sarcastic, ambiguous, and context-dependent. We explore whether providing contextual information, specifically user profile summaries derived from historical posts, can improve classification accuracy. Using a real-world political forum dataset, we generate structured profiles that summarize users’ ideological leaning, recurring topics, and linguistic patterns. We evaluate seven state-of-the-art LLMs across baseline and context-enriched setups through a comprehensive cross-model evaluation. Our findings show that contextual prompts significantly boost accuracy, with improvements ranging from +17.5% to +38.5%, achieving up to 74% accuracy that surpasses previous approaches. We also analyze how profile size and post selection strategies affect performance, showing that strategically chosen political content yields better results than larger, randomly selected contexts. These findings underscore the value of incorporating user-level context to enhance LLM performance in nuanced political classification tasks.</abstract>
<identifier type="citekey">sucu-etal-2025-exploiting</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.86</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.86/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1097</start>
<end>1110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting contextual information to improve stance detection in informal political discourse with LLMs
%A Sucu, Arman Engin
%A Zhou, Yixiang
%A Nascimento, Mario A.
%A Mullen, Tony
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F sucu-etal-2025-exploiting
%X This study investigates the use of Large Language Models (LLMs) for political stance detection in informal online discourse, where language is often sarcastic, ambiguous, and context-dependent. We explore whether providing contextual information, specifically user profile summaries derived from historical posts, can improve classification accuracy. Using a real-world political forum dataset, we generate structured profiles that summarize users’ ideological leaning, recurring topics, and linguistic patterns. We evaluate seven state-of-the-art LLMs across baseline and context-enriched setups through a comprehensive cross-model evaluation. Our findings show that contextual prompts significantly boost accuracy, with improvements ranging from +17.5% to +38.5%, achieving up to 74% accuracy that surpasses previous approaches. We also analyze how profile size and post selection strategies affect performance, showing that strategically chosen political content yields better results than larger, randomly selected contexts. These findings underscore the value of incorporating user-level context to enhance LLM performance in nuanced political classification tasks.
%R 10.18653/v1/2025.acl-srw.86
%U https://aclanthology.org/2025.acl-srw.86/
%U https://doi.org/10.18653/v1/2025.acl-srw.86
%P 1097-1110
Markdown (Informal)
[Exploiting contextual information to improve stance detection in informal political discourse with LLMs](https://aclanthology.org/2025.acl-srw.86/) (Sucu et al., ACL 2025)
ACL