@inproceedings{chen-etal-2024-go,
title = "What Can Go Wrong in Authorship Profiling: Cross-Domain Analysis of Gender and Age Prediction",
author = "Chen, Hongyu and
Roth, Michael and
Falenska, Agnieszka",
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Goldfarb-Tarrant, Seraphina and
Nozza, Debora",
booktitle = "Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.gebnlp-1.9",
pages = "150--166",
abstract = "Authorship Profiling (AP) aims to predict the demographic attributes (such as gender and age) of authors based on their writing styles. Ever-improving models mean that this task is gaining interest and application possibilities. However, with greater use also comes the risk that authors are misclassified more frequently, and it remains unclear to what extent the better models can capture the bias and who is affected by the models{'} mistakes. In this paper, we investigate three established datasets for AP as well as classical and neural classifiers for this task. Our analyses show that it is often possible to predict the demographic information of the authors based on textual features. However, some features learned by the models are specific to datasets. Moreover, models are prone to errors based on stereotypes associated with topical bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-go">
<titleInfo>
<title>What Can Go Wrong in Authorship Profiling: Cross-Domain Analysis of Gender and Age Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Falenska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seraphina</namePart>
<namePart type="family">Goldfarb-Tarrant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Authorship Profiling (AP) aims to predict the demographic attributes (such as gender and age) of authors based on their writing styles. Ever-improving models mean that this task is gaining interest and application possibilities. However, with greater use also comes the risk that authors are misclassified more frequently, and it remains unclear to what extent the better models can capture the bias and who is affected by the models’ mistakes. In this paper, we investigate three established datasets for AP as well as classical and neural classifiers for this task. Our analyses show that it is often possible to predict the demographic information of the authors based on textual features. However, some features learned by the models are specific to datasets. Moreover, models are prone to errors based on stereotypes associated with topical bias.</abstract>
<identifier type="citekey">chen-etal-2024-go</identifier>
<location>
<url>https://aclanthology.org/2024.gebnlp-1.9</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>150</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Can Go Wrong in Authorship Profiling: Cross-Domain Analysis of Gender and Age Prediction
%A Chen, Hongyu
%A Roth, Michael
%A Falenska, Agnieszka
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Goldfarb-Tarrant, Seraphina
%Y Nozza, Debora
%S Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chen-etal-2024-go
%X Authorship Profiling (AP) aims to predict the demographic attributes (such as gender and age) of authors based on their writing styles. Ever-improving models mean that this task is gaining interest and application possibilities. However, with greater use also comes the risk that authors are misclassified more frequently, and it remains unclear to what extent the better models can capture the bias and who is affected by the models’ mistakes. In this paper, we investigate three established datasets for AP as well as classical and neural classifiers for this task. Our analyses show that it is often possible to predict the demographic information of the authors based on textual features. However, some features learned by the models are specific to datasets. Moreover, models are prone to errors based on stereotypes associated with topical bias.
%U https://aclanthology.org/2024.gebnlp-1.9
%P 150-166
Markdown (Informal)
[What Can Go Wrong in Authorship Profiling: Cross-Domain Analysis of Gender and Age Prediction](https://aclanthology.org/2024.gebnlp-1.9) (Chen et al., GeBNLP-WS 2024)
ACL