@inproceedings{parfenova-etal-2024-automating,
title = "Automating Qualitative Data Analysis with Large Language Models",
author = {Parfenova, Angelina and
Denzler, Alexander and
Pfeffer, J{\"o}rgen},
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-srw.17/",
doi = "10.18653/v1/2024.acl-srw.17",
pages = "83--91",
abstract = "This PhD proposal aims to investigate ways of automating qualitative data analysis, specifically the thematic coding of texts. Despite existing methods vastly covered in literature, they mainly use Topic Modeling and other quantitative approaches which are far from resembling a human`s analysis outcome. This proposal examines the limitations of current research in the field. It proposes a novel methodology based on Large Language Models to tackle automated coding and make it as close as possible to the results of human researchers. This paper covers studies already done in this field and their limitations, existing software, the problem of duplicating the researcher bias, and the proposed methodology."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parfenova-etal-2024-automating">
<titleInfo>
<title>Automating Qualitative Data Analysis with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angelina</namePart>
<namePart type="family">Parfenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Denzler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörgen</namePart>
<namePart type="family">Pfeffer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This PhD proposal aims to investigate ways of automating qualitative data analysis, specifically the thematic coding of texts. Despite existing methods vastly covered in literature, they mainly use Topic Modeling and other quantitative approaches which are far from resembling a human‘s analysis outcome. This proposal examines the limitations of current research in the field. It proposes a novel methodology based on Large Language Models to tackle automated coding and make it as close as possible to the results of human researchers. This paper covers studies already done in this field and their limitations, existing software, the problem of duplicating the researcher bias, and the proposed methodology.</abstract>
<identifier type="citekey">parfenova-etal-2024-automating</identifier>
<identifier type="doi">10.18653/v1/2024.acl-srw.17</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-srw.17/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>83</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automating Qualitative Data Analysis with Large Language Models
%A Parfenova, Angelina
%A Denzler, Alexander
%A Pfeffer, Jörgen
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F parfenova-etal-2024-automating
%X This PhD proposal aims to investigate ways of automating qualitative data analysis, specifically the thematic coding of texts. Despite existing methods vastly covered in literature, they mainly use Topic Modeling and other quantitative approaches which are far from resembling a human‘s analysis outcome. This proposal examines the limitations of current research in the field. It proposes a novel methodology based on Large Language Models to tackle automated coding and make it as close as possible to the results of human researchers. This paper covers studies already done in this field and their limitations, existing software, the problem of duplicating the researcher bias, and the proposed methodology.
%R 10.18653/v1/2024.acl-srw.17
%U https://aclanthology.org/2024.luhme-srw.17/
%U https://doi.org/10.18653/v1/2024.acl-srw.17
%P 83-91
Markdown (Informal)
[Automating Qualitative Data Analysis with Large Language Models](https://aclanthology.org/2024.luhme-srw.17/) (Parfenova et al., ACL 2024)
ACL
- Angelina Parfenova, Alexander Denzler, and Jörgen Pfeffer. 2024. Automating Qualitative Data Analysis with Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 83–91, Bangkok, Thailand. Association for Computational Linguistics.