@inproceedings{munoz-sanchez-etal-2024-names,
title = "Did the Names {I} Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring",
author = {Mu{\~n}oz S{\'a}nchez, Ricardo and
Dobnik, Simon and
Szawerna, Maria Irena and
Lindstr{\"o}m Tiedemann, Therese and
Volodina, Elena},
editor = {Volodina, Elena and
Alfter, David and
Dobnik, Simon and
Lindstr{\"o}m Tiedemann, Therese and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Szawerna, Maria Irena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.caldpseudo-1.10/",
pages = "81--91",
abstract = "Automated essay scoring (AES) of second-language learner essays is a high-stakes task as it can affect the job and educational opportunities a student may have access to. Thus, it becomes imperative to make sure that the essays are graded based on the students' language proficiency as opposed to other reasons, such as personal names used in the text of the essay. Moreover, most of the research data for AES tends to contain personal identifiable information. Because of that, pseudonymization becomes an important tool to make sure that this data can be freely shared. Thus, our systems should not grade students based on which given names were used in the text of the essay, both for fairness and for privacy reasons. In this paper we explore how given names affect the CEFR level classification of essays of second language learners of Swedish. We use essays containing just one personal name and substitute it for names from lists of given names from four different ethnic origins, namely Swedish, Finnish, Anglo-American, and Arabic. We find that changing the names within the essays has no apparent effect on the classification task, regardless of whether a feature-based or a transformer-based model is used."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="munoz-sanchez-etal-2024-names">
<titleInfo>
<title>Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated essay scoring (AES) of second-language learner essays is a high-stakes task as it can affect the job and educational opportunities a student may have access to. Thus, it becomes imperative to make sure that the essays are graded based on the students’ language proficiency as opposed to other reasons, such as personal names used in the text of the essay. Moreover, most of the research data for AES tends to contain personal identifiable information. Because of that, pseudonymization becomes an important tool to make sure that this data can be freely shared. Thus, our systems should not grade students based on which given names were used in the text of the essay, both for fairness and for privacy reasons. In this paper we explore how given names affect the CEFR level classification of essays of second language learners of Swedish. We use essays containing just one personal name and substitute it for names from lists of given names from four different ethnic origins, namely Swedish, Finnish, Anglo-American, and Arabic. We find that changing the names within the essays has no apparent effect on the classification task, regardless of whether a feature-based or a transformer-based model is used.</abstract>
<identifier type="citekey">munoz-sanchez-etal-2024-names</identifier>
<location>
<url>https://aclanthology.org/2024.caldpseudo-1.10/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>81</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring
%A Muñoz Sánchez, Ricardo
%A Dobnik, Simon
%A Szawerna, Maria Irena
%A Lindström Tiedemann, Therese
%A Volodina, Elena
%Y Volodina, Elena
%Y Alfter, David
%Y Dobnik, Simon
%Y Lindström Tiedemann, Therese
%Y Muñoz Sánchez, Ricardo
%Y Szawerna, Maria Irena
%Y Vu, Xuan-Son
%S Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F munoz-sanchez-etal-2024-names
%X Automated essay scoring (AES) of second-language learner essays is a high-stakes task as it can affect the job and educational opportunities a student may have access to. Thus, it becomes imperative to make sure that the essays are graded based on the students’ language proficiency as opposed to other reasons, such as personal names used in the text of the essay. Moreover, most of the research data for AES tends to contain personal identifiable information. Because of that, pseudonymization becomes an important tool to make sure that this data can be freely shared. Thus, our systems should not grade students based on which given names were used in the text of the essay, both for fairness and for privacy reasons. In this paper we explore how given names affect the CEFR level classification of essays of second language learners of Swedish. We use essays containing just one personal name and substitute it for names from lists of given names from four different ethnic origins, namely Swedish, Finnish, Anglo-American, and Arabic. We find that changing the names within the essays has no apparent effect on the classification task, regardless of whether a feature-based or a transformer-based model is used.
%U https://aclanthology.org/2024.caldpseudo-1.10/
%P 81-91
Markdown (Informal)
[Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring](https://aclanthology.org/2024.caldpseudo-1.10/) (Muñoz Sánchez et al., CALD-pseudo 2024)
ACL