Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media

Asif Khan; Huaping Zhang; Nada Boudjellal; Bashir Hayat; Lin Dai; Arshad Ahmad; Ahmed Al-Hamed

doi:10.1007/978-981-19-9331-2_14

Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media

Asif Khan, Huaping Zhang^*, Nada Boudjellal, Bashir Hayat, Lin Dai, Arshad Ahmad, Ahmed Al-Hamed

^*Corresponding author for this work

School of Computer Science and Technology

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

Abstract

By the beginning of 2020, the world woke up to a global pandemic that changed people’s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people’s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters’ opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter’s data. Mainly two types of experiments were conducted and compared; (i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55).

Original language	English
Title of host publication	Proceedings of International Conference on Information Technology and Applications - ICITA 2022
Editors	Sajid Anwar, Abrar Ullah, Álvaro Rocha, Maria José Sousa
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	163-173
Number of pages	11
ISBN (Print)	9789811993305
DOIs	https://doi.org/10.1007/978-981-19-9331-2_14
Publication status	Published - 2023
Event	16th International Conference on Information Technology and Applications, ICITA 2022 - Lisbon, Portugal Duration: 20 Oct 2022 → 22 Oct 2022

Publication series

Name	Lecture Notes in Networks and Systems
Volume	614 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	16th International Conference on Information Technology and Applications, ICITA 2022
Country/Territory	Portugal
City	Lisbon
Period	20/10/22 → 22/10/22

Keywords

COVID-19
Election Prediction
Rule-based
Sentiment Analysis
Transformers
Twitter
USA Presidential Election

Access to Document

10.1007/978-981-19-9331-2_14

Cite this

Khan, A., Zhang, H., Boudjellal, N., Hayat, B., Dai, L., Ahmad, A., & Al-Hamed, A. (2023). Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media. In S. Anwar, A. Ullah, Á. Rocha, & M. J. Sousa (Eds.), Proceedings of International Conference on Information Technology and Applications - ICITA 2022 (pp. 163-173). (Lecture Notes in Networks and Systems; Vol. 614 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-9331-2_14

Khan, Asif ; Zhang, Huaping ; Boudjellal, Nada et al. / Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media. Proceedings of International Conference on Information Technology and Applications - ICITA 2022. editor / Sajid Anwar ; Abrar Ullah ; Álvaro Rocha ; Maria José Sousa. Springer Science and Business Media Deutschland GmbH, 2023. pp. 163-173 (Lecture Notes in Networks and Systems).

@inproceedings{b16c09400d9a4451baafd589e4820043,

title = "Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media",

abstract = "By the beginning of 2020, the world woke up to a global pandemic that changed people{\textquoteright}s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people{\textquoteright}s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters{\textquoteright} opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter{\textquoteright}s data. Mainly two types of experiments were conducted and compared; (i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55).",

keywords = "COVID-19, Election Prediction, Rule-based, Sentiment Analysis, Transformers, Twitter, USA Presidential Election",

author = "Asif Khan and Huaping Zhang and Nada Boudjellal and Bashir Hayat and Lin Dai and Arshad Ahmad and Ahmed Al-Hamed",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 16th International Conference on Information Technology and Applications, ICITA 2022 ; Conference date: 20-10-2022 Through 22-10-2022",

year = "2023",

doi = "10.1007/978-981-19-9331-2_14",

language = "English",

isbn = "9789811993305",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "163--173",

editor = "Sajid Anwar and Abrar Ullah and {\'A}lvaro Rocha and Sousa, {Maria Jos{\'e}}",

booktitle = "Proceedings of International Conference on Information Technology and Applications - ICITA 2022",

address = "Germany",

}

Khan, A, Zhang, H, Boudjellal, N, Hayat, B, Dai, L, Ahmad, A & Al-Hamed, A 2023, Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media. in S Anwar, A Ullah, Á Rocha & MJ Sousa (eds), Proceedings of International Conference on Information Technology and Applications - ICITA 2022. Lecture Notes in Networks and Systems, vol. 614 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 163-173, 16th International Conference on Information Technology and Applications, ICITA 2022, Lisbon, Portugal, 20/10/22. https://doi.org/10.1007/978-981-19-9331-2_14

Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media. / Khan, Asif; Zhang, Huaping; Boudjellal, Nada et al.
Proceedings of International Conference on Information Technology and Applications - ICITA 2022. ed. / Sajid Anwar; Abrar Ullah; Álvaro Rocha; Maria José Sousa. Springer Science and Business Media Deutschland GmbH, 2023. p. 163-173 (Lecture Notes in Networks and Systems; Vol. 614 LNNS).

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

TY - GEN

T1 - Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media

AU - Khan, Asif

AU - Zhang, Huaping

AU - Boudjellal, Nada

AU - Hayat, Bashir

AU - Dai, Lin

AU - Ahmad, Arshad

AU - Al-Hamed, Ahmed

PY - 2023

Y1 - 2023

N2 - By the beginning of 2020, the world woke up to a global pandemic that changed people’s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people’s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters’ opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter’s data. Mainly two types of experiments were conducted and compared; (i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55).

AB - By the beginning of 2020, the world woke up to a global pandemic that changed people’s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people’s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters’ opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter’s data. Mainly two types of experiments were conducted and compared; (i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55).

KW - COVID-19

KW - Election Prediction

KW - Rule-based

KW - Sentiment Analysis

KW - Transformers

KW - Twitter

KW - USA Presidential Election

UR - http://www.scopus.com/inward/record.url?scp=85161175649&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-9331-2_14

DO - 10.1007/978-981-19-9331-2_14

M3 - Conference contribution

AN - SCOPUS:85161175649

SN - 9789811993305

T3 - Lecture Notes in Networks and Systems

SP - 163

EP - 173

BT - Proceedings of International Conference on Information Technology and Applications - ICITA 2022

A2 - Anwar, Sajid

A2 - Ullah, Abrar

A2 - Rocha, Álvaro

A2 - Sousa, Maria José

PB - Springer Science and Business Media Deutschland GmbH

T2 - 16th International Conference on Information Technology and Applications, ICITA 2022

Y2 - 20 October 2022 through 22 October 2022

ER -

Khan A, Zhang H, Boudjellal N, Hayat B, Dai L, Ahmad A et al. Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media. In Anwar S, Ullah A, Rocha Á, Sousa MJ, editors, Proceedings of International Conference on Information Technology and Applications - ICITA 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 163-173. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-19-9331-2_14

Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this