@inproceedings{garland-etal-2020-countering,
title = "Countering hate on social media: Large scale classification of hate and counter speech",
author = "Garland, Joshua and
Ghazi-Zahedi, Keyan and
Young, Jean-Gabriel and
H{\'e}bert-Dufresne, Laurent and
Galesic, Mirta",
editor = "Akiwowo, Seyi and
Vidgen, Bertie and
Prabhakaran, Vinodkumar and
Waseem, Zeerak",
booktitle = "Proceedings of the Fourth Workshop on Online Abuse and Harms",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.alw-1.13",
doi = "10.18653/v1/2020.alw-1.13",
pages = "102--112",
abstract = "Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage with hate speech to restore civil non-polarized discourse. However, its actual effectiveness in curbing the spread of hatred is unknown and hard to quantify. One major obstacle to researching this question is a lack of large labeled data sets for training automated classifiers to identify counter speech. Here we use a unique situation in Germany where self-labeling groups engaged in organized online hate and counter speech. We use an ensemble learning algorithm which pairs a variety of paragraph embeddings with regularized logistic regression functions to classify both hate and counter speech in a corpus of millions of relevant tweets from these two groups. Our pipeline achieves macro F1 scores on out of sample balanced test sets ranging from 0.76 to 0.97{---}accuracy in line and even exceeding the state of the art. We then use the classifier to discover hate and counter speech in more than 135,000 fully-resolved Twitter conversations occurring from 2013 to 2018 and study their frequency and interaction. Altogether, our results highlight the potential of automated methods to evaluate the impact of coordinated counter speech in stabilizing conversations on social media.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garland-etal-2020-countering">
<titleInfo>
<title>Countering hate on social media: Large scale classification of hate and counter speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Garland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keyan</namePart>
<namePart type="family">Ghazi-Zahedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Gabriel</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Hébert-Dufresne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirta</namePart>
<namePart type="family">Galesic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Online Abuse and Harms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seyi</namePart>
<namePart type="family">Akiwowo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</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>Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage with hate speech to restore civil non-polarized discourse. However, its actual effectiveness in curbing the spread of hatred is unknown and hard to quantify. One major obstacle to researching this question is a lack of large labeled data sets for training automated classifiers to identify counter speech. Here we use a unique situation in Germany where self-labeling groups engaged in organized online hate and counter speech. We use an ensemble learning algorithm which pairs a variety of paragraph embeddings with regularized logistic regression functions to classify both hate and counter speech in a corpus of millions of relevant tweets from these two groups. Our pipeline achieves macro F1 scores on out of sample balanced test sets ranging from 0.76 to 0.97—accuracy in line and even exceeding the state of the art. We then use the classifier to discover hate and counter speech in more than 135,000 fully-resolved Twitter conversations occurring from 2013 to 2018 and study their frequency and interaction. Altogether, our results highlight the potential of automated methods to evaluate the impact of coordinated counter speech in stabilizing conversations on social media.</abstract>
<identifier type="citekey">garland-etal-2020-countering</identifier>
<identifier type="doi">10.18653/v1/2020.alw-1.13</identifier>
<location>
<url>https://aclanthology.org/2020.alw-1.13</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>102</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Countering hate on social media: Large scale classification of hate and counter speech
%A Garland, Joshua
%A Ghazi-Zahedi, Keyan
%A Young, Jean-Gabriel
%A Hébert-Dufresne, Laurent
%A Galesic, Mirta
%Y Akiwowo, Seyi
%Y Vidgen, Bertie
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the Fourth Workshop on Online Abuse and Harms
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F garland-etal-2020-countering
%X Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage with hate speech to restore civil non-polarized discourse. However, its actual effectiveness in curbing the spread of hatred is unknown and hard to quantify. One major obstacle to researching this question is a lack of large labeled data sets for training automated classifiers to identify counter speech. Here we use a unique situation in Germany where self-labeling groups engaged in organized online hate and counter speech. We use an ensemble learning algorithm which pairs a variety of paragraph embeddings with regularized logistic regression functions to classify both hate and counter speech in a corpus of millions of relevant tweets from these two groups. Our pipeline achieves macro F1 scores on out of sample balanced test sets ranging from 0.76 to 0.97—accuracy in line and even exceeding the state of the art. We then use the classifier to discover hate and counter speech in more than 135,000 fully-resolved Twitter conversations occurring from 2013 to 2018 and study their frequency and interaction. Altogether, our results highlight the potential of automated methods to evaluate the impact of coordinated counter speech in stabilizing conversations on social media.
%R 10.18653/v1/2020.alw-1.13
%U https://aclanthology.org/2020.alw-1.13
%U https://doi.org/10.18653/v1/2020.alw-1.13
%P 102-112
Markdown (Informal)
[Countering hate on social media: Large scale classification of hate and counter speech](https://aclanthology.org/2020.alw-1.13) (Garland et al., ALW 2020)
ACL