@inproceedings{tan-etal-2023-botpercent,
title = "{B}ot{P}ercent: Estimating Bot Populations in {T}witter Communities",
author = "Tan, Zhaoxuan and
Feng, Shangbin and
Sclar, Melanie and
Wan, Herun and
Luo, Minnan and
Choi, Yejin and
Tsvetkov, Yulia",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.954",
doi = "10.18653/v1/2023.findings-emnlp.954",
pages = "14295--14312",
abstract = "Twitter bot detection is vital in combating misinformation and safeguarding the integrity of social media discourse. While malicious bots are becoming more and more sophisticated and personalized, standard bot detection approaches are still agnostic to social environments (henceforth, communities) the bots operate at. In this work, we introduce community-specific bot detection, estimating the percentage of bots given the context of a community. Our method{---}BotPercent{---}is an amalgamation of Twitter bot detection datasets and feature-, text-, and graph-based models, adjusted to a particular community on Twitter. We introduce an approach that performs confidence calibration across bot detection models, which addresses generalization issues in existing community-agnostic models targeting individual bots and leads to more accurate community-level bot estimations. Experiments demonstrate that BotPercent achieves state-of-the-art performance in community-level Twitter bot detection across both balanced and imbalanced class distribution settings, presenting a less biased estimator of Twitter bot populations within the communities we analyze. We then analyze bot rates in several Twitter groups, including users who engage with partisan news media, political communities in different countries, and more. Our results reveal that the presence of Twitter bots is not homogeneous, but exhibiting a spatial-temporal distribution with considerable heterogeneity that should be taken into account for content moderation and social media policy making. The implementation of BotPercent is available at https://github.com/TamSiuhin/BotPercent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2023-botpercent">
<titleInfo>
<title>BotPercent: Estimating Bot Populations in Twitter Communities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaoxuan</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangbin</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Sclar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Herun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minnan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Twitter bot detection is vital in combating misinformation and safeguarding the integrity of social media discourse. While malicious bots are becoming more and more sophisticated and personalized, standard bot detection approaches are still agnostic to social environments (henceforth, communities) the bots operate at. In this work, we introduce community-specific bot detection, estimating the percentage of bots given the context of a community. Our method—BotPercent—is an amalgamation of Twitter bot detection datasets and feature-, text-, and graph-based models, adjusted to a particular community on Twitter. We introduce an approach that performs confidence calibration across bot detection models, which addresses generalization issues in existing community-agnostic models targeting individual bots and leads to more accurate community-level bot estimations. Experiments demonstrate that BotPercent achieves state-of-the-art performance in community-level Twitter bot detection across both balanced and imbalanced class distribution settings, presenting a less biased estimator of Twitter bot populations within the communities we analyze. We then analyze bot rates in several Twitter groups, including users who engage with partisan news media, political communities in different countries, and more. Our results reveal that the presence of Twitter bots is not homogeneous, but exhibiting a spatial-temporal distribution with considerable heterogeneity that should be taken into account for content moderation and social media policy making. The implementation of BotPercent is available at https://github.com/TamSiuhin/BotPercent.</abstract>
<identifier type="citekey">tan-etal-2023-botpercent</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.954</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.954</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14295</start>
<end>14312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BotPercent: Estimating Bot Populations in Twitter Communities
%A Tan, Zhaoxuan
%A Feng, Shangbin
%A Sclar, Melanie
%A Wan, Herun
%A Luo, Minnan
%A Choi, Yejin
%A Tsvetkov, Yulia
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F tan-etal-2023-botpercent
%X Twitter bot detection is vital in combating misinformation and safeguarding the integrity of social media discourse. While malicious bots are becoming more and more sophisticated and personalized, standard bot detection approaches are still agnostic to social environments (henceforth, communities) the bots operate at. In this work, we introduce community-specific bot detection, estimating the percentage of bots given the context of a community. Our method—BotPercent—is an amalgamation of Twitter bot detection datasets and feature-, text-, and graph-based models, adjusted to a particular community on Twitter. We introduce an approach that performs confidence calibration across bot detection models, which addresses generalization issues in existing community-agnostic models targeting individual bots and leads to more accurate community-level bot estimations. Experiments demonstrate that BotPercent achieves state-of-the-art performance in community-level Twitter bot detection across both balanced and imbalanced class distribution settings, presenting a less biased estimator of Twitter bot populations within the communities we analyze. We then analyze bot rates in several Twitter groups, including users who engage with partisan news media, political communities in different countries, and more. Our results reveal that the presence of Twitter bots is not homogeneous, but exhibiting a spatial-temporal distribution with considerable heterogeneity that should be taken into account for content moderation and social media policy making. The implementation of BotPercent is available at https://github.com/TamSiuhin/BotPercent.
%R 10.18653/v1/2023.findings-emnlp.954
%U https://aclanthology.org/2023.findings-emnlp.954
%U https://doi.org/10.18653/v1/2023.findings-emnlp.954
%P 14295-14312
Markdown (Informal)
[BotPercent: Estimating Bot Populations in Twitter Communities](https://aclanthology.org/2023.findings-emnlp.954) (Tan et al., Findings 2023)
ACL
- Zhaoxuan Tan, Shangbin Feng, Melanie Sclar, Herun Wan, Minnan Luo, Yejin Choi, and Yulia Tsvetkov. 2023. BotPercent: Estimating Bot Populations in Twitter Communities. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14295–14312, Singapore. Association for Computational Linguistics.