@inproceedings{zenimoto-etal-2024-coding,
title = "Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models",
author = "Zenimoto, Yuki and
Hasegawa, Ryo and
Utsuro, Takehito and
Yoshioka, Masaharu and
Kando, Noriko",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.26",
pages = "242--254",
abstract = "Survey research using open-ended responses is an important method thatcontributes to the discovery of unknown issues and new needs. However,survey research generally requires time and cost-consuming manual dataprocessing, indicating that it is difficult to analyze large dataset.To address this issue, we propose an LLM-based method to automate partsof the grounded theory approach (GTA), a representative approach of thequalitative data analysis. We generated and annotated pseudo open-endedresponses, and used them as the training data for the coding proceduresof GTA. Through evaluations, we showed that the models trained withpseudo open-ended responses are quite effective compared with thosetrained with manually annotated open-ended responses. We alsodemonstrate that the LLM-based approach is highly efficient andcost-saving compared to human-based approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zenimoto-etal-2024-coding">
<titleInfo>
<title>Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Zenimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Hasegawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaharu</namePart>
<namePart type="family">Yoshioka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noriko</namePart>
<namePart type="family">Kando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Survey research using open-ended responses is an important method thatcontributes to the discovery of unknown issues and new needs. However,survey research generally requires time and cost-consuming manual dataprocessing, indicating that it is difficult to analyze large dataset.To address this issue, we propose an LLM-based method to automate partsof the grounded theory approach (GTA), a representative approach of thequalitative data analysis. We generated and annotated pseudo open-endedresponses, and used them as the training data for the coding proceduresof GTA. Through evaluations, we showed that the models trained withpseudo open-ended responses are quite effective compared with thosetrained with manually annotated open-ended responses. We alsodemonstrate that the LLM-based approach is highly efficient andcost-saving compared to human-based approach.</abstract>
<identifier type="citekey">zenimoto-etal-2024-coding</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.26</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>242</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models
%A Zenimoto, Yuki
%A Hasegawa, Ryo
%A Utsuro, Takehito
%A Yoshioka, Masaharu
%A Kando, Noriko
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zenimoto-etal-2024-coding
%X Survey research using open-ended responses is an important method thatcontributes to the discovery of unknown issues and new needs. However,survey research generally requires time and cost-consuming manual dataprocessing, indicating that it is difficult to analyze large dataset.To address this issue, we propose an LLM-based method to automate partsof the grounded theory approach (GTA), a representative approach of thequalitative data analysis. We generated and annotated pseudo open-endedresponses, and used them as the training data for the coding proceduresof GTA. Through evaluations, we showed that the models trained withpseudo open-ended responses are quite effective compared with thosetrained with manually annotated open-ended responses. We alsodemonstrate that the LLM-based approach is highly efficient andcost-saving compared to human-based approach.
%U https://aclanthology.org/2024.naacl-srw.26
%P 242-254
Markdown (Informal)
[Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models](https://aclanthology.org/2024.naacl-srw.26) (Zenimoto et al., NAACL 2024)
ACL
- Yuki Zenimoto, Ryo Hasegawa, Takehito Utsuro, Masaharu Yoshioka, and Noriko Kando. 2024. Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 242–254, Mexico City, Mexico. Association for Computational Linguistics.