@inproceedings{akter-etal-2025-costs,
title = "Costs and Benefits of {AI}-Enabled Topic Modeling in {P}-20 Research: The Case of School Improvement Plans",
author = "Akter, Syeda Sabrina and
Hunter, Seth and
Woo, David and
Anastasopoulos, Antonios",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.34/",
doi = "10.18653/v1/2025.bea-1.34",
pages = "460--476",
ISBN = "979-8-89176-270-1",
abstract = "As generative AI tools become increasingly integrated into educational research workflows, large language models (LLMs) have shown substantial promise in automating complex tasks such as topic modeling. This paper presents a user study that evaluates AI-enabled topic modeling (AITM) within the domain of P-20 education research. We investigate the benefits and trade-offs of integrating LLMs into expert document analysis through a case study of school improvement plans, comparing four analytical conditions. Our analysis focuses on three dimensions: (1) the marginal financial and environmental costs of AITM, (2) the impact of LLM assistance on annotation time, and (3) the influence of AI suggestions on topic identification. The results show that LLM increases efficiency and decreases financial cost, but potentially introduce anchoring bias that awareness prompts alone fail to mitigate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akter-etal-2025-costs">
<titleInfo>
<title>Costs and Benefits of AI-Enabled Topic Modeling in P-20 Research: The Case of School Improvement Plans</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syeda</namePart>
<namePart type="given">Sabrina</namePart>
<namePart type="family">Akter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Hunter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Woo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</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">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>As generative AI tools become increasingly integrated into educational research workflows, large language models (LLMs) have shown substantial promise in automating complex tasks such as topic modeling. This paper presents a user study that evaluates AI-enabled topic modeling (AITM) within the domain of P-20 education research. We investigate the benefits and trade-offs of integrating LLMs into expert document analysis through a case study of school improvement plans, comparing four analytical conditions. Our analysis focuses on three dimensions: (1) the marginal financial and environmental costs of AITM, (2) the impact of LLM assistance on annotation time, and (3) the influence of AI suggestions on topic identification. The results show that LLM increases efficiency and decreases financial cost, but potentially introduce anchoring bias that awareness prompts alone fail to mitigate.</abstract>
<identifier type="citekey">akter-etal-2025-costs</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.34</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.34/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>460</start>
<end>476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Costs and Benefits of AI-Enabled Topic Modeling in P-20 Research: The Case of School Improvement Plans
%A Akter, Syeda Sabrina
%A Hunter, Seth
%A Woo, David
%A Anastasopoulos, Antonios
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F akter-etal-2025-costs
%X As generative AI tools become increasingly integrated into educational research workflows, large language models (LLMs) have shown substantial promise in automating complex tasks such as topic modeling. This paper presents a user study that evaluates AI-enabled topic modeling (AITM) within the domain of P-20 education research. We investigate the benefits and trade-offs of integrating LLMs into expert document analysis through a case study of school improvement plans, comparing four analytical conditions. Our analysis focuses on three dimensions: (1) the marginal financial and environmental costs of AITM, (2) the impact of LLM assistance on annotation time, and (3) the influence of AI suggestions on topic identification. The results show that LLM increases efficiency and decreases financial cost, but potentially introduce anchoring bias that awareness prompts alone fail to mitigate.
%R 10.18653/v1/2025.bea-1.34
%U https://aclanthology.org/2025.bea-1.34/
%U https://doi.org/10.18653/v1/2025.bea-1.34
%P 460-476
Markdown (Informal)
[Costs and Benefits of AI-Enabled Topic Modeling in P-20 Research: The Case of School Improvement Plans](https://aclanthology.org/2025.bea-1.34/) (Akter et al., BEA 2025)
ACL