@inproceedings{williams-etal-2024-dodo,
title = "{D}o{D}o Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures",
author = "Williams, Angus Redlarski and
Kirk, Hannah Rose and
Burke-Moore, Liam and
Chung, Yi-Ling and
Debono, Ivan and
Johansson, Pica and
Stevens, Francesca and
Bright, Jonathan and
Hale, Scott",
editor = "Kumar, Ritesh and
Ojha, Atul Kr. and
Malmasi, Shervin and
Chakravarthi, Bharathi Raja and
Lahiri, Bornini and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the Fourth Workshop on Threat, Aggression {\&} Cyberbullying @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.trac-1.15",
pages = "134--154",
abstract = "Public figures receive disproportionate levels of abuse on social media, impacting their active participation in public life. Automated systems can identify abuse at scale but labelling training data is expensive and potentially harmful. So, it is desirable that systems are efficient and generalisable, handling shared and specific aspects of abuse. We explore the dynamics of cross-group text classification in order to understand how well models trained on one domain or demographic can transfer to others, with a view to building more generalisable abuse classifiers. We fine-tune language models to classify tweets targeted at public figures using our novel DoDo dataset, containing 28,000 entries with fine-grained labels, split equally across four Domain-Demographic pairs (male and female footballers and politicians). We find that (i) small amounts of diverse data are hugely beneficial to generalisation and adaptation; (ii) models transfer more easily across demographics but cross-domain models are more generalisable; (iii) some groups contribute more to generalisability than others; and (iv) dataset similarity is a signal of transferability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="williams-etal-2024-dodo">
<titleInfo>
<title>DoDo Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angus</namePart>
<namePart type="given">Redlarski</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Kirk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liam</namePart>
<namePart type="family">Burke-Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Debono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pica</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Stevens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Bright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Hale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Public figures receive disproportionate levels of abuse on social media, impacting their active participation in public life. Automated systems can identify abuse at scale but labelling training data is expensive and potentially harmful. So, it is desirable that systems are efficient and generalisable, handling shared and specific aspects of abuse. We explore the dynamics of cross-group text classification in order to understand how well models trained on one domain or demographic can transfer to others, with a view to building more generalisable abuse classifiers. We fine-tune language models to classify tweets targeted at public figures using our novel DoDo dataset, containing 28,000 entries with fine-grained labels, split equally across four Domain-Demographic pairs (male and female footballers and politicians). We find that (i) small amounts of diverse data are hugely beneficial to generalisation and adaptation; (ii) models transfer more easily across demographics but cross-domain models are more generalisable; (iii) some groups contribute more to generalisability than others; and (iv) dataset similarity is a signal of transferability.</abstract>
<identifier type="citekey">williams-etal-2024-dodo</identifier>
<location>
<url>https://aclanthology.org/2024.trac-1.15</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>134</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DoDo Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures
%A Williams, Angus Redlarski
%A Kirk, Hannah Rose
%A Burke-Moore, Liam
%A Chung, Yi-Ling
%A Debono, Ivan
%A Johansson, Pica
%A Stevens, Francesca
%A Bright, Jonathan
%A Hale, Scott
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Malmasi, Shervin
%Y Chakravarthi, Bharathi Raja
%Y Lahiri, Bornini
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F williams-etal-2024-dodo
%X Public figures receive disproportionate levels of abuse on social media, impacting their active participation in public life. Automated systems can identify abuse at scale but labelling training data is expensive and potentially harmful. So, it is desirable that systems are efficient and generalisable, handling shared and specific aspects of abuse. We explore the dynamics of cross-group text classification in order to understand how well models trained on one domain or demographic can transfer to others, with a view to building more generalisable abuse classifiers. We fine-tune language models to classify tweets targeted at public figures using our novel DoDo dataset, containing 28,000 entries with fine-grained labels, split equally across four Domain-Demographic pairs (male and female footballers and politicians). We find that (i) small amounts of diverse data are hugely beneficial to generalisation and adaptation; (ii) models transfer more easily across demographics but cross-domain models are more generalisable; (iii) some groups contribute more to generalisability than others; and (iv) dataset similarity is a signal of transferability.
%U https://aclanthology.org/2024.trac-1.15
%P 134-154
Markdown (Informal)
[DoDo Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures](https://aclanthology.org/2024.trac-1.15) (Williams et al., TRAC-WS 2024)
ACL
- Angus Redlarski Williams, Hannah Rose Kirk, Liam Burke-Moore, Yi-Ling Chung, Ivan Debono, Pica Johansson, Francesca Stevens, Jonathan Bright, and Scott Hale. 2024. DoDo Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures. In Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024, pages 134–154, Torino, Italia. ELRA and ICCL.