@inproceedings{bezirhan-von-davier-2025-ai,
title = "{AI}-Based Classification of {TIMSS} Items for Framework Alignment",
author = "Bezirhan, Ummugul and
von Davier, Matthias",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
month = oct,
year = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-main.15/",
pages = "134--141",
ISBN = "979-8-218-84228-4",
abstract = "Large-scale assessments rely on expert panels to verify that test items align with prescribed frameworks, a labor-intensive process. This study evaluates the use of GPT-4o to classify TIMSS items to content domain, cognitive domain, and difficulty categories. Findings highlight the potential of language models to support scalable, framework-aligned item verification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bezirhan-von-davier-2025-ai">
<titleInfo>
<title>AI-Based Classification of TIMSS Items for Framework Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ummugul</namePart>
<namePart type="family">Bezirhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">von Davier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-218-84228-4</identifier>
</relatedItem>
<abstract>Large-scale assessments rely on expert panels to verify that test items align with prescribed frameworks, a labor-intensive process. This study evaluates the use of GPT-4o to classify TIMSS items to content domain, cognitive domain, and difficulty categories. Findings highlight the potential of language models to support scalable, framework-aligned item verification.</abstract>
<identifier type="citekey">bezirhan-von-davier-2025-ai</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.15/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>134</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI-Based Classification of TIMSS Items for Framework Alignment
%A Bezirhan, Ummugul
%A von Davier, Matthias
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F bezirhan-von-davier-2025-ai
%X Large-scale assessments rely on expert panels to verify that test items align with prescribed frameworks, a labor-intensive process. This study evaluates the use of GPT-4o to classify TIMSS items to content domain, cognitive domain, and difficulty categories. Findings highlight the potential of language models to support scalable, framework-aligned item verification.
%U https://aclanthology.org/2025.aimecon-main.15/
%P 134-141
Markdown (Informal)
[AI-Based Classification of TIMSS Items for Framework Alignment](https://aclanthology.org/2025.aimecon-main.15/) (Bezirhan & von Davier, AIME-Con 2025)
ACL
- Ummugul Bezirhan and Matthias von Davier. 2025. AI-Based Classification of TIMSS Items for Framework Alignment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 134–141, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).