Analysis of COVID-19 Offensive Tweets and Their Targets

Song Liao; Ebuka Okpala; Long Cheng; Mingqi Li; Nishant Vishwamitra; Hongxin Hu; Feng Luo; Matthew Costello

doi:10.1145/3580305.3599773

Analysis of COVID-19 Offensive Tweets and Their Targets

Song Liao
, Ebuka Okpala
, Long Cheng
, Mingqi Li
, Nishant Vishwamitra
, Hongxin Hu
, Feng Luo
, Matthew Costello

Department of Computer Science and Engineering

Clemson University
University of Texas at San Antonio

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

During the global COVID-19 pandemic, people utilized social media platforms, especially Twitter, to spread and express opinions about the pandemic. Such discussions also drove the rise in COVID-related offensive speech. In this work, focusing on Twitter, we present a comprehensive analysis of COVID-related offensive tweets and their targets. We collected a COVID-19 dataset with over 747 million tweets for 30 months and fine-tuned a BERT classifier to detect offensive tweets. Our offensive tweets analysis shows that the ebb and flow of COVID-related offensive tweets potentially reflect events in the physical world. We then studied the targets of these offensive tweets. There was a large number of offensive tweets with abusive words, which could negatively affect the targeted groups or individuals. We also conducted a user network analysis, and found that offensive users interact more with other offensive users and that the pandemic had a lasting impact on some offensive users.

Original language	English
Title of host publication	KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	4473-4484
Number of pages	12
ISBN (Electronic)	9798400701030
DOIs	https://doi.org/10.1145/3580305.3599773
State	Published - Aug 4 2023
Event	29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States Duration: Aug 6 2023 → Aug 10 2023

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISSN (Print)	2154-817X

Conference

Conference	29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Country/Territory	United States
City	Long Beach
Period	08/6/23 → 08/10/23

Keywords

covid-19
offensive tweets
twitter

Access to Document

10.1145/3580305.3599773

Cite this

Liao, S., Okpala, E., Cheng, L., Li, M., Vishwamitra, N., Hu, H., Luo, F., & Costello, M. (2023). Analysis of COVID-19 Offensive Tweets and Their Targets. In KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 4473-4484). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery . https://doi.org/10.1145/3580305.3599773

@inproceedings{b9e4db904a5f462aa0e99a02a8fa1574,

title = "Analysis of COVID-19 Offensive Tweets and Their Targets",

abstract = "During the global COVID-19 pandemic, people utilized social media platforms, especially Twitter, to spread and express opinions about the pandemic. Such discussions also drove the rise in COVID-related offensive speech. In this work, focusing on Twitter, we present a comprehensive analysis of COVID-related offensive tweets and their targets. We collected a COVID-19 dataset with over 747 million tweets for 30 months and fine-tuned a BERT classifier to detect offensive tweets. Our offensive tweets analysis shows that the ebb and flow of COVID-related offensive tweets potentially reflect events in the physical world. We then studied the targets of these offensive tweets. There was a large number of offensive tweets with abusive words, which could negatively affect the targeted groups or individuals. We also conducted a user network analysis, and found that offensive users interact more with other offensive users and that the pandemic had a lasting impact on some offensive users.",

keywords = "covid-19, offensive tweets, twitter",

author = "Song Liao and Ebuka Okpala and Long Cheng and Mingqi Li and Nishant Vishwamitra and Hongxin Hu and Feng Luo and Matthew Costello",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 ; Conference date: 06-08-2023 Through 10-08-2023",

year = "2023",

month = aug,

day = "4",

doi = "10.1145/3580305.3599773",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery ",

pages = "4473--4484",

booktitle = "KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

address = "United States",

}

Liao, S, Okpala, E, Cheng, L, Li, M, Vishwamitra, N, Hu, H, Luo, F & Costello, M 2023, Analysis of COVID-19 Offensive Tweets and Their Targets. in KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery , pp. 4473-4484, 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Long Beach, United States, 08/6/23. https://doi.org/10.1145/3580305.3599773

Analysis of COVID-19 Offensive Tweets and Their Targets. / Liao, Song; Okpala, Ebuka; Cheng, Long et al.
KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery , 2023. p. 4473-4484 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analysis of COVID-19 Offensive Tweets and Their Targets

AU - Liao, Song

AU - Okpala, Ebuka

AU - Cheng, Long

AU - Li, Mingqi

AU - Vishwamitra, Nishant

AU - Hu, Hongxin

AU - Luo, Feng

AU - Costello, Matthew

PY - 2023/8/4

Y1 - 2023/8/4

N2 - During the global COVID-19 pandemic, people utilized social media platforms, especially Twitter, to spread and express opinions about the pandemic. Such discussions also drove the rise in COVID-related offensive speech. In this work, focusing on Twitter, we present a comprehensive analysis of COVID-related offensive tweets and their targets. We collected a COVID-19 dataset with over 747 million tweets for 30 months and fine-tuned a BERT classifier to detect offensive tweets. Our offensive tweets analysis shows that the ebb and flow of COVID-related offensive tweets potentially reflect events in the physical world. We then studied the targets of these offensive tweets. There was a large number of offensive tweets with abusive words, which could negatively affect the targeted groups or individuals. We also conducted a user network analysis, and found that offensive users interact more with other offensive users and that the pandemic had a lasting impact on some offensive users.

AB - During the global COVID-19 pandemic, people utilized social media platforms, especially Twitter, to spread and express opinions about the pandemic. Such discussions also drove the rise in COVID-related offensive speech. In this work, focusing on Twitter, we present a comprehensive analysis of COVID-related offensive tweets and their targets. We collected a COVID-19 dataset with over 747 million tweets for 30 months and fine-tuned a BERT classifier to detect offensive tweets. Our offensive tweets analysis shows that the ebb and flow of COVID-related offensive tweets potentially reflect events in the physical world. We then studied the targets of these offensive tweets. There was a large number of offensive tweets with abusive words, which could negatively affect the targeted groups or individuals. We also conducted a user network analysis, and found that offensive users interact more with other offensive users and that the pandemic had a lasting impact on some offensive users.

KW - covid-19

KW - offensive tweets

KW - twitter

UR - https://www.scopus.com/pages/publications/85171344800

U2 - 10.1145/3580305.3599773

DO - 10.1145/3580305.3599773

M3 - Conference contribution

AN - SCOPUS:85171344800

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 4473

EP - 4484

BT - KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

T2 - 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023

Y2 - 6 August 2023 through 10 August 2023

ER -

Liao S, Okpala E, Cheng L, Li M, Vishwamitra N, Hu H et al. Analysis of COVID-19 Offensive Tweets and Their Targets. In KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery . 2023. p. 4473-4484. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3580305.3599773

Analysis of COVID-19 Offensive Tweets and Their Targets

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this