@inproceedings{omrani-etal-2024-towards,
title = "Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning",
author = "Omrani, Ali and
Salkhordeh Ziabari, Alireza and
Golazizian, Preni and
Sorensen, Jeffrey and
Dehghani, Morteza",
editor = {Chung, Yi-Ling and
Talat, Zeerak and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
R{\"o}ttger, Paul and
Mostafazadeh Davani, Aida and
Calabrese, Agostina},
booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.woah-1.7",
doi = "10.18653/v1/2024.woah-1.7",
pages = "68--109",
abstract = "Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia and in industry, to develop annotated resources that capture various aspects of problematic content. Due to researchers{'} diverse objectives, these annotations are often inconsistent and hence, reports of progress on the detection of problematic content are fragmented. This pattern is expected to persist unless we pool these resources, taking into account the dynamic nature of this issue. In this paper, we propose integrating the available resources, leveraging their dynamic nature to break this pattern, and introduce a continual learning framework and benchmark for problematic content detection. Our benchmark, comprising 84 related tasks, creates a novel measure of progress: prioritizing the adaptability of classifiers to evolving tasks over excelling in specific tasks. To ensure continuous relevance, our benchmark is designed for seamless integration of new tasks. Our results demonstrate that continual learning methods outperform static approaches by up to 17{\%} and 4{\%} AUC in capturing the evolving content and adapting to novel forms of problematic content",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="omrani-etal-2024-towards">
<titleInfo>
<title>Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Omrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alireza</namePart>
<namePart type="family">Salkhordeh Ziabari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preni</namePart>
<namePart type="family">Golazizian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Sorensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Dehghani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</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>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Röttger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia and in industry, to develop annotated resources that capture various aspects of problematic content. Due to researchers’ diverse objectives, these annotations are often inconsistent and hence, reports of progress on the detection of problematic content are fragmented. This pattern is expected to persist unless we pool these resources, taking into account the dynamic nature of this issue. In this paper, we propose integrating the available resources, leveraging their dynamic nature to break this pattern, and introduce a continual learning framework and benchmark for problematic content detection. Our benchmark, comprising 84 related tasks, creates a novel measure of progress: prioritizing the adaptability of classifiers to evolving tasks over excelling in specific tasks. To ensure continuous relevance, our benchmark is designed for seamless integration of new tasks. Our results demonstrate that continual learning methods outperform static approaches by up to 17% and 4% AUC in capturing the evolving content and adapting to novel forms of problematic content</abstract>
<identifier type="citekey">omrani-etal-2024-towards</identifier>
<identifier type="doi">10.18653/v1/2024.woah-1.7</identifier>
<location>
<url>https://aclanthology.org/2024.woah-1.7</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>68</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning
%A Omrani, Ali
%A Salkhordeh Ziabari, Alireza
%A Golazizian, Preni
%A Sorensen, Jeffrey
%A Dehghani, Morteza
%Y Chung, Yi-Ling
%Y Talat, Zeerak
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Röttger, Paul
%Y Mostafazadeh Davani, Aida
%Y Calabrese, Agostina
%S Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F omrani-etal-2024-towards
%X Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia and in industry, to develop annotated resources that capture various aspects of problematic content. Due to researchers’ diverse objectives, these annotations are often inconsistent and hence, reports of progress on the detection of problematic content are fragmented. This pattern is expected to persist unless we pool these resources, taking into account the dynamic nature of this issue. In this paper, we propose integrating the available resources, leveraging their dynamic nature to break this pattern, and introduce a continual learning framework and benchmark for problematic content detection. Our benchmark, comprising 84 related tasks, creates a novel measure of progress: prioritizing the adaptability of classifiers to evolving tasks over excelling in specific tasks. To ensure continuous relevance, our benchmark is designed for seamless integration of new tasks. Our results demonstrate that continual learning methods outperform static approaches by up to 17% and 4% AUC in capturing the evolving content and adapting to novel forms of problematic content
%R 10.18653/v1/2024.woah-1.7
%U https://aclanthology.org/2024.woah-1.7
%U https://doi.org/10.18653/v1/2024.woah-1.7
%P 68-109
Markdown (Informal)
[Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning](https://aclanthology.org/2024.woah-1.7) (Omrani et al., WOAH-WS 2024)
ACL