From associations to sarcasm: Mining the shift of opinions regarding the Supreme Court on twitter☆
Introduction
Research on Twitter and politics covers both elite and public use of Twitter. Elite-centered studies consider which political officials use Twitter, how, and for what purposes. Who uses Twitter has been of particular interest in studies of congressional members [1], [2], [3], and campaign-focused research has looked at gender differences in congressional candidates’ Twitter use [4]. The content of elected officials’ tweets can be a key to understanding what activities officials prioritize in office (e.g. [5], [6]). Scholars have also relied on tweets to gain insight into the relationship between elected officials and their constituents or followers on Twitter (e.g. [7], [8]). Recognizing journalists’ reliance on Twitter, some studies focus on elite Twitter users’ influence on media coverage in the context of political campaigns [9] and in governing [10].
Many scholars have turned to Twitter to learn more about the political behavior, opinion, and communication of the public. Three areas of study have gained considerable attention: Twitter in the context of campaigns and in the development of social movements, the effects of Twitter on political interest, and the rhetoric and tone in political tweets. Campaign studies have examined the effectiveness of candidate messages delivered via Twitter compared to messages voters receive from traditional news media [11]. Tweets in campaigns have been analyzed in several ways [12] including to provide evidence of ideological echo chambers [13], compare the spread of fake news and corrections of such stories [14], and study citizens’ perceptions of candidates [15] and responses to candidate speeches [16]. Numerous studies exist on the role of Twitter in social movements, particularly the use of social media to react to events and encourage the formation of collective identities that result in activism (e.g. [17], [18], [19], [20]). And there have been efforts to demonstrate the political effects of Twitter on the public; for example, Bode and Dalrymple [21] found in a survey that Twitter users were more interested in politics and less trusting of mainstream media, suggesting important implications for political communication. Twitter is an excellent source for rhetorical studies with scholars using tweets to examine incivility, sarcasm, and the use of humor in political discourse [22], [23], [24].
The messages produced on Twitter (i.e., tweets) may be analyzed qualitatively as researchers read them, or they may be automatically examined through a computational lens. Automatically finding patterns in the data produced on social websites is known as social web mining, and specifically Twitter mining when the social platform of interest is only Twitter [25]. A very large number of tweets is one of the key reasons to perform Twitter mining instead of, or in complement to, a qualitative approach. For instance, the phenomenon of interest may only be observed through a massive amount of data, such as tracking the monthly opinions of various communities in each US state over months. Although Twitter mining may lack the depth or nuance of qualitative methods on individual tweets, coping with datasets consisting of millions of tweets requires a computational method and special infrastructure [26]. Such large datasets are either impossible to process for a team of researchers, or would limit researchers to simple forms of qualitative analyses that can be accurately performed via crowdsourcing. Twitter mining is a well-established approach in health behaviors [27], [28], [29], for instance by analyzing foods consumed using 503 million tweets [30]. Our approach applies Twitter mining to the 2018 confirmation of Judge Brett Kavanaugh. This topic was previously analyzed by Darwish, who used 23 million tweets to analyze the polarization of 687,194 users [31]. While the work of Darwish focuses on polarization around Kavanaugh, we analyze a less direct effect: whether the Kavanaugh case changes public opinion about the Supreme Court itself. Our first research question thus contributes to the literature on politics and media:
- (Q1)
Is there a shift in the public opinion of the Supreme Court before and after the confirmation of Judge Brett Kavanaugh?
The analysis of political discourse on Twitter has its own challenges, in part due to the use of incivility, sarcasm, and humor. Sarcasm has been the topic of numeroxml us papers on Twitter mining [32], whose methodologies range from a reliance on self-disclosure of sarcasm (e.g., via the hashtags #sarcasm or #sarcastic [33], [34]) to the use of advanced artificial tools such as neural networks [35]. In this paper, our second research question is whether sarcasm does matter for Twitter mining in the context of political discourse. Formally, our question is:
- (Q2)
Can sarcasm in political messages posted on Twitter significantly alter the results of computational methods even when using large datasets?
The remainder of this paper is organized as follows. In Section 2, we provide a succinct background to the context of our case study, that is, the confirmation of Judge Brett Kavanaugh. Given this context, we introduce our methods in Section 3, in line with the framework that we recently used in Sandhu et al. [36]. In Section 4, we provide our results on the case study. The final section contextualizes our results with respect to our two research questions, and concludes with suggestions for future work.
Section snippets
Background
When United States Supreme Court Justice Anthony Kennedy decided to retire in the summer of 2018, the process to confirm Federal Appellate Court Judge Brett Kavanaugh to replace him was inevitably going to be partisan. Democrats were still angry that the Republican majority in the Senate had denied former President Barack Obama the opportunity to appoint a replacement for conservative Justice Antonin Scalia, who had died unexpectedly during Obama’s last year in office. Refusing to hold
Overview
To date, research on Twitter and politics has incorporated a variety of methodologies. There have been qualitative analyses of relatively small samples of tweets [3], [9], often combined with other qualitative methods including elite interviews. The majority of quantitative studies rely on content analysis of tweets from varying sample sizes. The studies often select tweets that include a particular hashtag [18], [20], occur within a specified time period [24], or come from specific political
Results
Our two analyses examined the presence of associations and then the types of sentiments (section 3.4). The results for both analyses are presented in turn. We confirmed 4 out of 7 potential associations (57%) on the October dataset, and 5 out of 7 (71%) on the November dataset (Fig. 5). Most importantly, the association between the Supreme Court and Partisan was confirmed in November but not in October. That is, after the confirmation of Judge Brett Kavanaugh, the Supreme Court was associated
Discussion
Twitter has been analyzed in numerous studies to further our understanding of the political behavior, opinion, and communication of the public. While qualitative analyses have demonstrated their usefulness in capturing the nuance of tweets, automatic approaches (i.e., ‘Twitter mining’) can provide a useful complement to analyze large datasets formed of millions of tweets. A challenge in this situation is the use of incivility, sarcasm, and humor. Our work provides a technical contribution to
Conclusion
By automatically analyzing millions of tweets, we find evidence of a shift in the public opinion of the Supreme Court before and after the confirmation of Judge Brett Kavanaugh. The Supreme Court was associated with partisanship one month after the confirmation but not in the days that immediately followed. We also demonstrate that sarcasm in political tweets can alter the outcome of tweet mining even when using large datasets.
Contributions
The study was initiated by PJG and VKM, with input from CDV. PJG designed the methods. MS wrote the scripts to generate the results and analyzed them. PJG and CDV wrote the first version of the manuscript. MS performed additional experiments for the revision and, together with PJG, wrote the Appendix. All authors read and approved of this manuscript.
Declaration of Competing Interest
None.
Acknowledgments
The authors are indebted to Mitacs Canada for providing the financial support which allowed MS to perform this research at Furman University, while mentored by other members of the team. We thank Chetan Harichandra Mendhe and an NSERC Discovery Grant to VKM for developing and use the infrastructure that gathered the tweets for this data.
References (71)
To tweet or not to tweet: exploring the determinants of early adoption of twitter by house members in the 111th congress
Social Sci. J.
(2012)- et al.
A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis
Expert Syst. Appl.
(2018) - et al.
Sarcastic sentiment detection in tweets streamed in real time: a big data approach
Digital Commun. Netw.
(2016) - et al.
Orsim: Integrating existing software components to detect similar natural language requirements
CEUR Workshop Proceedings
(2018) - et al.
Creating groups with similar expected behavioural response in randomized controlled trials: a fuzzy cognitive map approach
BMC Med. Res. Methodol.
(2014) - et al.
The artificial facilitator: guiding participants in developing causal maps using voice-activated technologies
International Conference on Human-Computer Interaction
(2019) - et al.
Congressional social media communications: evaluating senate twitter usage
Online Inf. Rev.
(2016) Congress and the Media: Beyond Institutional Power
(2017)- et al.
I am woman, hear me tweet! gender differences in twitter use among congressional candidates
J. Women Politics Policy
(2017) - et al.
Congressional twitter use revisited on the platform’s 10-year anniversary
J. Assoc. Inf. Sci. Technol.
(2018)
The politics of prioritization: senators’ attention in 140 characters
The Forum, volume 16
Politics and the Twitter Revolution: How Tweets Influence the Relationship between Political Leaders and the Public
Follower-followee network, communication networks, and vote agreement of the us members of congress
Commun. Res.
Seizing the moment: the presidential campaigns’ use of twitter during the 2012 electoral cycle
New Media Soc.
Political influencers. a study of Donald Trump’s personal brand on twitter and its impact on the media and users.
Commun. Soc.
Twitter versus the traditional media: a survey experiment comparing public perceptions of campaign messages in the 2016 us presidential election
Social Sci. Comput. Rev.
Twitter use in election campaigns: a systematic literature review
J. Inf. Technol. Politics
You too, second screeners? second screeners’ echo chambers during the 2016 us elections primaries
J. Broadcast. Electron. Media
Political rumoring on twitter during the 2012 us presidential election: rumor diffusion and correction
New Media Soc.
Perceptions of presidential candidates’ personalities in twitter
J. Assoc. Inf. Sci. Technol.
When presidential candidates voice party issues, does twitter listen?
J. Elections Public Opin. Parties
Networked gatekeeping and networked framing on# egypt
Int. J. Press/Politics
I was grabbed by my pussy and its# notokay: a twitter backlash against donald trump’s degrading commentary
Violence Against Women
How# blacklivesmatter: exploring the role of hip-hop celebrities in constructing racial identity on black twitter
Inf. Commun. Soc.
Ferguson and the death of michael brown on twitter:# blacklivesmatter,# tcot, and the evolution of collective identities
Ethnic Racial Stud.
Politics in 140 characters or less: campaign communication, network interaction, and political participation on twitter
J. Political Market.
The age of twitter: Donald j. trump and the politics of debasement
Crit. Stud. Media Commun.
Social media, science, and attack discourse: how twitter discussions of climate change use sarcasm and incivility
Sci. Commun.
Seriously funny: the political work of humor on social media
New Media Soc.
Twitter mining for discovery, prediction and causality: applications and methodologies
Intell. Syst. Account. FinanceManag.
A framework for social media data analytics using elasticsearch and kibana
Wirel. Netw.
Obesity in social media: a mixed methods analysis
Transl. Behav. Med.
Computational content analysis of negative tweets for obesity, diet, diabetes, and exercise
Proc. Assoc. Inf. Sci. Technol.
Estimating county health statistics with twitter
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
You tweet what you eat: Studying food consumption through twitter
Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems
Cited by (0)
- ☆
Research funded by MITACS Globalink Research Award, Canada.