@inproceedings{palomino-etal-2021-goldenwind,
title = "{G}olden{W}ind at {S}em{E}val-2021 Task 5: Orthrus - An Ensemble Approach to Identify Toxicity",
author = "Palomino, Marco and
Grad, Dawid and
Bedwell, James",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.115/",
doi = "10.18653/v1/2021.semeval-1.115",
pages = "860--864",
abstract = "Many new developments to detect and mitigate toxicity are currently being evaluated. We are particularly interested in the correlation between toxicity and the emotions expressed in online posts. While toxicity may be disguised by amending the wording of posts, emotions will not. Therefore, we describe here an ensemble method to identify toxicity and classify the emotions expressed on a corpus of annotated posts published by Task 5 of SemEval 2021{--}our analysis shows that the majority of such posts express anger, sadness and fear. Our method to identify toxicity combines a lexicon-based approach, which on its own achieves an F1 score of 61.07{\%}, with a supervised learning approach, which on its own achieves an F1 score of 60{\%}. When both methods are combined, the ensemble achieves an F1 score of 66.37{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palomino-etal-2021-goldenwind">
<titleInfo>
<title>GoldenWind at SemEval-2021 Task 5: Orthrus - An Ensemble Approach to Identify Toxicity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Palomino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Grad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Bedwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many new developments to detect and mitigate toxicity are currently being evaluated. We are particularly interested in the correlation between toxicity and the emotions expressed in online posts. While toxicity may be disguised by amending the wording of posts, emotions will not. Therefore, we describe here an ensemble method to identify toxicity and classify the emotions expressed on a corpus of annotated posts published by Task 5 of SemEval 2021–our analysis shows that the majority of such posts express anger, sadness and fear. Our method to identify toxicity combines a lexicon-based approach, which on its own achieves an F1 score of 61.07%, with a supervised learning approach, which on its own achieves an F1 score of 60%. When both methods are combined, the ensemble achieves an F1 score of 66.37%.</abstract>
<identifier type="citekey">palomino-etal-2021-goldenwind</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.115</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.115/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>860</start>
<end>864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GoldenWind at SemEval-2021 Task 5: Orthrus - An Ensemble Approach to Identify Toxicity
%A Palomino, Marco
%A Grad, Dawid
%A Bedwell, James
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F palomino-etal-2021-goldenwind
%X Many new developments to detect and mitigate toxicity are currently being evaluated. We are particularly interested in the correlation between toxicity and the emotions expressed in online posts. While toxicity may be disguised by amending the wording of posts, emotions will not. Therefore, we describe here an ensemble method to identify toxicity and classify the emotions expressed on a corpus of annotated posts published by Task 5 of SemEval 2021–our analysis shows that the majority of such posts express anger, sadness and fear. Our method to identify toxicity combines a lexicon-based approach, which on its own achieves an F1 score of 61.07%, with a supervised learning approach, which on its own achieves an F1 score of 60%. When both methods are combined, the ensemble achieves an F1 score of 66.37%.
%R 10.18653/v1/2021.semeval-1.115
%U https://aclanthology.org/2021.semeval-1.115/
%U https://doi.org/10.18653/v1/2021.semeval-1.115
%P 860-864
Markdown (Informal)
[GoldenWind at SemEval-2021 Task 5: Orthrus - An Ensemble Approach to Identify Toxicity](https://aclanthology.org/2021.semeval-1.115/) (Palomino et al., SemEval 2021)
ACL