Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models

Salam Albatarni; Tamer Elsayed

doi:10.63317/3co8wwdqqyf6

Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Quadratic Weighted Kappa (QWK) has been the standard evaluation metric in Automated Essay Scoring (AES) research for over two decades. Despite repeated criticisms highlighting its limitations, the community has largely continued to rely on QWK without adopting alternative metrics. This study aims to encourage a shift toward more suitable evaluation practices by systematically examining QWK’s behavior under three key conditions: dataset size, class imbalance, and score range. Using both a publicly available AES dataset and carefully synthesized datasets, we demonstrate scenarios where QWK produces unstable or misleading results. Our findings highlight the need for more robust evaluation practices and point to alternative metrics, particularly variants of Gwet’s AC2, that offer greater reliability across a variety of conditions.

Anthology ID:: 2026.lrec-1.348
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 4447–4456
Language:
External URL:: https://lrec.elra.info/lrec2026-main-348
DOI:: 10.63317/3co8wwdqqyf6
Bibkey:
Cite (ACL):: Salam Albatarni and Tamer Elsayed. 2026. Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4447–4456, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models (Albatarni & Elsayed, LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{albatarni-elsayed-2026-quadratic,
    title = "Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models",
    author = "Albatarni, Salam  and
      Elsayed, Tamer",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.348/",
    doi = "10.63317/3co8wwdqqyf6",
    pages = "4447--4456",
    abstract = "Quadratic Weighted Kappa (QWK) has been the standard evaluation metric in Automated Essay Scoring (AES) research for over two decades. Despite repeated criticisms highlighting its limitations, the community has largely continued to rely on QWK without adopting alternative metrics. This study aims to encourage a shift toward more suitable evaluation practices by systematically examining QWK{'}s behavior under three key conditions: dataset size, class imbalance, and score range. Using both a publicly available AES dataset and carefully synthesized datasets, we demonstrate scenarios where QWK produces unstable or misleading results. Our findings highlight the need for more robust evaluation practices and point to alternative metrics, particularly variants of Gwet{'}s AC2, that offer greater reliability across a variety of conditions."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albatarni-elsayed-2026-quadratic">
    <titleInfo>
        <title>Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Salam</namePart>
        <namePart type="family">Albatarni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tamer</namePart>
        <namePart type="family">Elsayed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Quadratic Weighted Kappa (QWK) has been the standard evaluation metric in Automated Essay Scoring (AES) research for over two decades. Despite repeated criticisms highlighting its limitations, the community has largely continued to rely on QWK without adopting alternative metrics. This study aims to encourage a shift toward more suitable evaluation practices by systematically examining QWK’s behavior under three key conditions: dataset size, class imbalance, and score range. Using both a publicly available AES dataset and carefully synthesized datasets, we demonstrate scenarios where QWK produces unstable or misleading results. Our findings highlight the need for more robust evaluation practices and point to alternative metrics, particularly variants of Gwet’s AC2, that offer greater reliability across a variety of conditions.</abstract>
    <identifier type="citekey">albatarni-elsayed-2026-quadratic</identifier>
    <identifier type="doi">10.63317/3co8wwdqqyf6</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.348/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>4447</start>
            <end>4456</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models
%A Albatarni, Salam
%A Elsayed, Tamer
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F albatarni-elsayed-2026-quadratic
%X Quadratic Weighted Kappa (QWK) has been the standard evaluation metric in Automated Essay Scoring (AES) research for over two decades. Despite repeated criticisms highlighting its limitations, the community has largely continued to rely on QWK without adopting alternative metrics. This study aims to encourage a shift toward more suitable evaluation practices by systematically examining QWK’s behavior under three key conditions: dataset size, class imbalance, and score range. Using both a publicly available AES dataset and carefully synthesized datasets, we demonstrate scenarios where QWK produces unstable or misleading results. Our findings highlight the need for more robust evaluation practices and point to alternative metrics, particularly variants of Gwet’s AC2, that offer greater reliability across a variety of conditions.
%R 10.63317/3co8wwdqqyf6
%U https://aclanthology.org/2026.lrec-1.348/
%U https://doi.org/10.63317/3co8wwdqqyf6
%P 4447-4456

Download as File

Markdown (Informal)

[Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models](https://aclanthology.org/2026.lrec-1.348/) (Albatarni & Elsayed, LREC 2026)

Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models (Albatarni & Elsayed, LREC 2026)

ACL

Salam Albatarni and Tamer Elsayed. 2026. Quadratic Weighted Kappa Is Not Enough for Evaluating Automated Essay Scoring Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4447–4456, Palma de Mallorca, Spain. ELRA Language Resource Association.