Sentiment, we-talk and engagement on social media: insights from Twitter data mining on the US presidential elections 2020

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Standard

Sentiment, we-talk and engagement on social media: insights from Twitter data mining on the US presidential elections 2020. / Hagemann, Linus; Abramova, Olga.
in: Internet Research, Jahrgang 33, Nr. 6, 27.11.2023, S. 2058-2085.

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{ebe92dba1d754a679149e965c628c2b4,
title = "Sentiment, we-talk and engagement on social media: insights from Twitter data mining on the US presidential elections 2020",
abstract = "Purpose: Given inconsistent results in prior studies, this paper applies the dual process theory to investigate what social media messages yield audience engagement during a political event. It tests how affective cues (emotional valence, intensity and collective self-representation) and cognitive cues (insight, causation, certainty and discrepancy) contribute to public engagement. Design/methodology/approach: The authors created a dataset of more than three million tweets during the 2020 United States (US) presidential elections. Affective and cognitive cues were assessed via sentiment analysis. The hypotheses were tested in negative binomial regressions. The authors also scrutinized a subsample of far-famed Twitter users. The final dataset, scraping code, preprocessing and analysis are available in an open repository. Findings: The authors found the prominence of both affective and cognitive cues. For the overall sample, negativity bias was registered, and the tweet{\textquoteright}s emotionality was negatively related to engagement. In contrast, in the sub-sample of tweets from famous users, emotionally charged content produced higher engagement. The role of sentiment decreases when the number of followers grows and ultimately becomes insignificant for Twitter participants with many followers. Collective self-representation (“we-talk”) is consistently associated with more likes, comments and retweets in the overall sample and subsamples. Originality/value: The authors expand the dominating one-sided perspective to social media message processing focused on the peripheral route and hence affective cues. Leaning on the dual process theory, the authors shed light on the effectiveness of both affective (peripheral route) and cognitive (central route) cues on information appeal and dissemination on Twitter during a political event. The popularity of the tweet{\textquoteright}s author moderates these relationships.",
keywords = "Big data, Data mining, Engagement, Social media, Business informatics, Informatics",
author = "Linus Hagemann and Olga Abramova",
note = "Funding Information: The current article is the extended version of the paper presented at the 55th Hawaii International Conference on System Sciences (HICSS 2022) (https://scholarspace.manoa.hawaii.edu/items/ec5b5c24-557a-4bb3-b94e-bcac0c74283b). The authors would like to thank Prof. Christy Cheung, the Internet Research editor, and two anonymous reviewers for the helpful comments. Publisher Copyright: {\textcopyright} 2022, Emerald Publishing Limited.; 55th Hawaii International Conference on System Sciences, HICSS 55 ; Conference date: 03-01-2022 Through 07-01-2022",
year = "2023",
month = nov,
day = "27",
doi = "10.1108/INTR-12-2021-0885",
language = "English",
volume = "33",
pages = "2058--2085",
journal = "Internet Research",
issn = "1066-2243",
publisher = "Emerald Publishing Limited",
number = "6",
url = "https://hicss.hawaii.edu/",

}

RIS

TY - JOUR

T1 - Sentiment, we-talk and engagement on social media

T2 - 55th Hawaii International Conference on System Sciences

AU - Hagemann, Linus

AU - Abramova, Olga

N1 - Conference code: 55

PY - 2023/11/27

Y1 - 2023/11/27

N2 - Purpose: Given inconsistent results in prior studies, this paper applies the dual process theory to investigate what social media messages yield audience engagement during a political event. It tests how affective cues (emotional valence, intensity and collective self-representation) and cognitive cues (insight, causation, certainty and discrepancy) contribute to public engagement. Design/methodology/approach: The authors created a dataset of more than three million tweets during the 2020 United States (US) presidential elections. Affective and cognitive cues were assessed via sentiment analysis. The hypotheses were tested in negative binomial regressions. The authors also scrutinized a subsample of far-famed Twitter users. The final dataset, scraping code, preprocessing and analysis are available in an open repository. Findings: The authors found the prominence of both affective and cognitive cues. For the overall sample, negativity bias was registered, and the tweet’s emotionality was negatively related to engagement. In contrast, in the sub-sample of tweets from famous users, emotionally charged content produced higher engagement. The role of sentiment decreases when the number of followers grows and ultimately becomes insignificant for Twitter participants with many followers. Collective self-representation (“we-talk”) is consistently associated with more likes, comments and retweets in the overall sample and subsamples. Originality/value: The authors expand the dominating one-sided perspective to social media message processing focused on the peripheral route and hence affective cues. Leaning on the dual process theory, the authors shed light on the effectiveness of both affective (peripheral route) and cognitive (central route) cues on information appeal and dissemination on Twitter during a political event. The popularity of the tweet’s author moderates these relationships.

AB - Purpose: Given inconsistent results in prior studies, this paper applies the dual process theory to investigate what social media messages yield audience engagement during a political event. It tests how affective cues (emotional valence, intensity and collective self-representation) and cognitive cues (insight, causation, certainty and discrepancy) contribute to public engagement. Design/methodology/approach: The authors created a dataset of more than three million tweets during the 2020 United States (US) presidential elections. Affective and cognitive cues were assessed via sentiment analysis. The hypotheses were tested in negative binomial regressions. The authors also scrutinized a subsample of far-famed Twitter users. The final dataset, scraping code, preprocessing and analysis are available in an open repository. Findings: The authors found the prominence of both affective and cognitive cues. For the overall sample, negativity bias was registered, and the tweet’s emotionality was negatively related to engagement. In contrast, in the sub-sample of tweets from famous users, emotionally charged content produced higher engagement. The role of sentiment decreases when the number of followers grows and ultimately becomes insignificant for Twitter participants with many followers. Collective self-representation (“we-talk”) is consistently associated with more likes, comments and retweets in the overall sample and subsamples. Originality/value: The authors expand the dominating one-sided perspective to social media message processing focused on the peripheral route and hence affective cues. Leaning on the dual process theory, the authors shed light on the effectiveness of both affective (peripheral route) and cognitive (central route) cues on information appeal and dissemination on Twitter during a political event. The popularity of the tweet’s author moderates these relationships.

KW - Big data

KW - Data mining

KW - Engagement

KW - Social media

KW - Business informatics

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=85146306399&partnerID=8YFLogxK

U2 - 10.1108/INTR-12-2021-0885

DO - 10.1108/INTR-12-2021-0885

M3 - Conference article in journal

AN - SCOPUS:85146306399

VL - 33

SP - 2058

EP - 2085

JO - Internet Research

JF - Internet Research

SN - 1066-2243

IS - 6

Y2 - 3 January 2022 through 7 January 2022

ER -

DOI