@inproceedings{kasianenko-etal-2024-detecting,
title = "Detecting Online Community Practices with Large Language Models: A Case Study of Pro-{U}krainian Publics on {T}witter",
author = "Kasianenko, Kateryna and
Khanehzar, Shima and
Wan, Stephen and
Dehghan, Ehsan and
Bruns, Axel",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1122/",
doi = "10.18653/v1/2024.emnlp-main.1122",
pages = "20106--20135",
abstract = "Communities on social media display distinct patterns of linguistic expression and behaviour, collectively referred to as practices. These practices can be traced in textual exchanges, and reflect the intentions, knowledge, values, and norms of users and communities. This paper introduces a comprehensive methodological workflow for computational identification of such practices within social media texts. By focusing on supporters of Ukraine during the Russia-Ukraine war in (1) the activist collective NAFO and (2) the Eurovision Twitter community, we present a gold-standard data set capturing their unique practices. Using this corpus, we perform practice prediction experiments with both open-source baseline models and OpenAI`s large language models (LLMs). Our results demonstrate that closed-source models, especially GPT-4, achieve superior performance, particularly with prompts that incorporate salient features of practices, or utilize Chain-of-Thought prompting. This study provides a detailed error analysis and offers valuable insights into improving the precision of practice identification, thereby supporting context-sensitive moderation and advancing the understanding of online community dynamics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kasianenko-etal-2024-detecting">
<titleInfo>
<title>Detecting Online Community Practices with Large Language Models: A Case Study of Pro-Ukrainian Publics on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kateryna</namePart>
<namePart type="family">Kasianenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shima</namePart>
<namePart type="family">Khanehzar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Dehghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="family">Bruns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Communities on social media display distinct patterns of linguistic expression and behaviour, collectively referred to as practices. These practices can be traced in textual exchanges, and reflect the intentions, knowledge, values, and norms of users and communities. This paper introduces a comprehensive methodological workflow for computational identification of such practices within social media texts. By focusing on supporters of Ukraine during the Russia-Ukraine war in (1) the activist collective NAFO and (2) the Eurovision Twitter community, we present a gold-standard data set capturing their unique practices. Using this corpus, we perform practice prediction experiments with both open-source baseline models and OpenAI‘s large language models (LLMs). Our results demonstrate that closed-source models, especially GPT-4, achieve superior performance, particularly with prompts that incorporate salient features of practices, or utilize Chain-of-Thought prompting. This study provides a detailed error analysis and offers valuable insights into improving the precision of practice identification, thereby supporting context-sensitive moderation and advancing the understanding of online community dynamics.</abstract>
<identifier type="citekey">kasianenko-etal-2024-detecting</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.1122</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1122/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>20106</start>
<end>20135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Online Community Practices with Large Language Models: A Case Study of Pro-Ukrainian Publics on Twitter
%A Kasianenko, Kateryna
%A Khanehzar, Shima
%A Wan, Stephen
%A Dehghan, Ehsan
%A Bruns, Axel
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kasianenko-etal-2024-detecting
%X Communities on social media display distinct patterns of linguistic expression and behaviour, collectively referred to as practices. These practices can be traced in textual exchanges, and reflect the intentions, knowledge, values, and norms of users and communities. This paper introduces a comprehensive methodological workflow for computational identification of such practices within social media texts. By focusing on supporters of Ukraine during the Russia-Ukraine war in (1) the activist collective NAFO and (2) the Eurovision Twitter community, we present a gold-standard data set capturing their unique practices. Using this corpus, we perform practice prediction experiments with both open-source baseline models and OpenAI‘s large language models (LLMs). Our results demonstrate that closed-source models, especially GPT-4, achieve superior performance, particularly with prompts that incorporate salient features of practices, or utilize Chain-of-Thought prompting. This study provides a detailed error analysis and offers valuable insights into improving the precision of practice identification, thereby supporting context-sensitive moderation and advancing the understanding of online community dynamics.
%R 10.18653/v1/2024.emnlp-main.1122
%U https://aclanthology.org/2024.emnlp-main.1122/
%U https://doi.org/10.18653/v1/2024.emnlp-main.1122
%P 20106-20135
Markdown (Informal)
[Detecting Online Community Practices with Large Language Models: A Case Study of Pro-Ukrainian Publics on Twitter](https://aclanthology.org/2024.emnlp-main.1122/) (Kasianenko et al., EMNLP 2024)
ACL