Retweet Network Research Articles

Bridging polarised Twitter discussions: the interactions of the users in the middle

PurposeThe purpose of the paper is to analyse the interactions of bridging users in Twitter discussions about vaccination.Design/methodology/approachConversational threads were collected through filtering the Twitter stream using keywords and the most active participants in the conversations. Following data collection and anonymisation of tweets and user profiles, a retweet network was created to find users bridging the main clusters. Four conversations were selected, ranging from 456 to 1,983 tweets long, and then analysed through content analysis.FindingsAlthough different opinions met in the discussions, a consensus was rarely built. Many sub-threads involved insults and criticism, and participants seemed not interested in shifting their positions. However, examples of reasoned discussions were also found.Originality/valueThe study analyses conversations on Twitter, which is rarely studied. The focus on the interactions of bridging users adds to the uniqueness of the paper.

Characterizing twitter user topics and communication network dynamics of the “Liberate” movement during COVID-19 using unsupervised machine learning and social network analysis

This paper analyzes online user conversation topics and discourse on Twitter related to the “Liberate” Protest movement in reaction to social distancing guidelines at the early stages of the COVID-19 pandemic. Interdisciplinary approaches in big data, machine learning, content analysis, and social network analysis (SNA) were used to characterize the communicative behavior, conversation themes, and network structures of Liberate protest supporters and non-supporters. Tweets were content coded and grouped within topic clusters produced from an unsupervised machine learning algorithm using natural language processing. An analysis of topic clusters found that tweets that support the protests are highly concentrated and have higher volumes of replicated tweets. Protest Supporters were also more likely to retweet other users while Non-Supporters were more likely to include a URL from an outside media source and produce a unique tweet. SNA was also used to assess the characteristics of retweet networks and found that the Protester Supporter network had a more centralized structure and was strongly influenced by a political organization, in contrast to the Non-Supporter network that had a larger number of smaller and more evenly-sized nodes and more driven by media personalities and commentators. Collectively, these characteristics indicate that protest supporters had more centralized, consistent and disseminated discourse protesting COVID-19 social distancing requirements compared to non-supporters who were more diverse in their criticism of the Liberate movement and generally more fragmented in their support of public health measures. Results from this study provide important insights into pandemic communication dynamics of opposing twitter communities, including in the context of those who oppose and support public health measures in a highly politicized social and online environment. Results are important in the context of assessing the messages, communication propagation and overall activities of social media communities in response to basic public health measures needed to contain this post-digital era global pandemic.

Public Discourse and Social Network Echo Chambers Driven by Socio-Cognitive Biases

In recent years, social media has become an important platform for political discourse, being a site of both political conversations between voters and political advertisements from campaigns. While their individual influences on public discourse are well documented, the interplay between individual-level cognitive biases, social influence processes, dueling campaign efforts, and social media platforms remains unexamined. We introduce an agent-based model that integrates these dynamics and illustrates how their combination can lead to the formation of echo chambers. We find that the range of political viewpoints that individuals are willing to consider is a key determinant in the formation of polarized networks and the emergence of echo chambers and show that aggressive political campaigns can have counterproductive outcomes by radicalizing supporters and alienating moderates. Our model results demonstrate how certain elements of public discourse and political polarization can be understood as the result of an interactive process of shifting individual opinions, evolving social networks, and political campaigns. We also introduce a dynamic empirical case, retweet networks from the final stage of the 2016 U.S. presidential election, to show how our proposed model can be calibrated with real-world behavior.8 MoreReceived 6 June 2020Revised 1 September 2020Accepted 27 October 2020DOI:https://doi.org/10.1103/PhysRevX.10.041042Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.Published by the American Physical SocietyPhysics Subject Headings (PhySH)Research AreasCommunity structureCompetitionEvolving networksSocial systemsPhysical SystemsSocial networksNetworks

Networked publics in #NoDAPL protests: Interactions among activist publics and influence of locality and proximity on socially mediated networks

Hashtag “#NoDAPL” was used by environmental activists for a series of protests against the construction of the Dakota Access Pipeline beginning in early 2016. Utilizing 2 million tweets with the main hashtag, as well as the auxiliary hashtags, from around 550,000 unique users between November 2016 and February 2017, the study investigated the interactions among four groups—regular activists, Native American activists, reporters, and organizations identified based on their bio information, and the effects of physical location on network attention. Exponential random graph models (ERGMs) on the retweet network showed that Native American activists occupied the most prominent positions and that different groups assumed different network roles. Location analysis based on Poisson regression showed that physical proximity’s effects on attention depended on group status, and the effects were moderated by users’ authority. Implications of the study results on networked publics and the influence of locality and proximity on socially mediated networks were discussed.

Predicting Politician’s Supporters’ Network on Twitter Using Social Network Analysis and Semantic Analysis

Politics is one of the hottest and most commonly mentioned and viewed topics on social media networks nowadays. Microblogging platforms like Twitter and Weibo are widely used by many politicians who have a huge number of followers and supporters on those platforms. It is essential to study the supporters’ network of political leaders because it can help in decision making when predicting their political futures. This study focuses on the supporters’ network of three famous political leaders of Pakistan, namely, Imran Khan (IK), Maryam Nawaz Sharif (MNS), and Bilawal Bhutto Zardari (BBZ). This is done using social network analysis and semantic analysis. The proposed method (1) detects and removes fake supporter(s), (2) mines communities in the politicians’ social network(s), (3) investigates the supporters’ reply network for conversations between supporters about each leader, and, finally, (4) analyses the retweet network for information diffusion of each political leader. Furthermore, sentiment analysis of the supporters of politicians is done using machine learning techniques, which ultimately predicted and revealed the strongest supporter network(s) among the three political leaders. Analysis of this data reveals that as of October 2017 (1) IK was the most renowned of the three politicians and had the strongest supporter’s community while using Twitter in a very controlled manner, (2) BBZ had the weakest supporters’ network on Twitter, and (3) the supporters of the political leaders in Pakistan are flexible on Twitter, communicating with each other, and that any group of supporters has a low level of isolation.

Effects of Information Veracity and Message Frames on Information Dissemination: A Case Study of 2016 Zika Epidemic Discussion on Twitter

ABSTRACT By taking the 2016 Zika outbreak as a case study, this research examines how information veracity (true information vs. misinformation) interacted with message frames to influence the dissemination of information about Zika through retweet networks. The four message frames examined in this study included legislation of funding, election, women’s human rights, and sports. In general, we discovered that misinformation about Zika did not outperform true information about Zika in terms of generating more retweets or attracting more users. However, on average, the retweet networks of misinformation about Zika had larger network diameter and higher structural virality than those of true information about Zika. Except for the sports frame, using any of the other three frames engaged more users in retweeting information about Zika than not using any frame, regardless of information accuracy. We also found that the four frames varied in their respective capacities of moderating the impact of information veracity on the dissemination of tweets about Zika. Implications of these findings are discussed in this paper.

Measuring Time-Constrained Influence to Predict Adoption in Online Social Networks

Recently, there has been strong interest in measuring influence in online social networks. Different measures have been proposed to predict when individuals will adopt a new behavior, given the influence produced by their friends. In this article, we show that one can achieve significant improvement over these measures, extending them to consider a pair of time constraints that provide a better proxy for social influence. By conducting an engineering study that investigates retweet networks from Twitter and Sina Weibo datasets, we tune those two parameters while we examine the correlation between influence and the probability of adoption, as well as the ability to predict adoption, estimating the real susceptibility and influence to which microblog users are dynamically subjected. Although there are limitations about using retweets to analyze social influence, our results show that for the simple count of active neighbors, its correlation with the probability of adoption is boosted up to 518.75%, whereas similar gains are observed for the other influence measures analyzed. We also obtain up to 18.89% improvement in F 1 score when compared to recent machine learning techniques that aim to predict adoption, enabling practical use of the corresponding concepts for social influence applications.

Real Talk About Fake News: Identity Language and Disconnected Networks of the US Public’s “Fake News” Discourse on Twitter

This article studies “fake news” beyond the consumption and dissemination of misinformation and disinformation. We uncover how the term “fake news” serves as a discursive device for ordinary citizens to consolidate group identity in everyday political utterances on Twitter. Using computational linguistic and network analyses, we demonstrate that over the period of 2016–2018, there is an uptrend in the use of identity language in US Twitter users’ discussions about “fake news,” manifested by the increased frequency of group pronouns in combination with issues and sentiments that boost one’s ingroup and derogate the outgroup. Furthermore, as opposed to the conventional wisdom that “fake news” is a right-wing term, we uncover two disconnected retweet networks surrounding liberal and conservative opinion leaders. Like-minded individuals selectively amplify ingroup messages to claim the power to define falsehood and make group-serving blame attributions. We discuss the theoretical implications of our findings and offer new directions for future research on “fake news,” misinformation, and disinformation.

Social awareness of crisis events: A new perspective from social-physical network

The emergence of social media provides a rich source of posts to facilitate situational awareness and management during crisis events. Since interactions within social media users are frequently used to establish social networks, previous studies have explored how social media contributes to the information diffusion about crisis events. However, most studies have concentrated on the dynamics of the online social network, whereas the information diffused within social space and physical world during different event evolution stages tends to be overlooked. To address this problem, this study introduces a methodology for modeling and analyzing the information diffusion of crisis events based on the retweet patterns of social media users at city level. The proposed methodology consists of two parts: 1) Fisher ordinal clustering method is applied to divide the evolution stages of crisis events based on social media user activities. 2) To explore the information diffusion of crisis events in the physical world, the social-physical network (SPnet) is constructed by extending the retweet network to the geographical space for each evolution stage. The Weibo data related to the Kunming terrorist attack in 2014 are analyzed to demonstrate the methodology. By identifying the geo-location of users (90.8% of the total active users), two types of SPnet are constructed based on the retweet patterns of ordinary users and media users, respectively. The results show that the information diffusion in the SPnet of ordinary users are mainly from Kunming, while in the SPnet of media users, major developed cities are the key nodes for information diffusion. This study provides useful insights for understanding how human activities react to crisis events through the social-physical network at city level.

Online reactions to the 2017 \u2018Unite the right\u2019 rally in Charlottesville: measuring polarization in Twitter networks using media followership

Network analysis of social media provides an important new lens on politics, communication, and their interactions. This lens is particularly prominent in fast-moving events, such as conversations and action in political rallies and the use of social media by extremist groups to spread their message. We study the Twitter conversation following the August 2017 ‘Unite the Right’ rally in Charlottesville, Virginia, USA using tools from network analysis and data science. We use media followership on Twitter and principal component analysis (PCA) to compute a ‘Left’/‘Right’ media score on a one-dimensional axis to characterize Twitter accounts. We then use these scores, in concert with retweet relationships, to examine the structure of a retweet network of approximately 300,000 accounts that communicated with the #Charlottesville hashtag. The retweet network is sharply polarized, with an assortativity coefficient of 0.8 with respect to the sign of the media PCA score. Community detection using two approaches, a Louvain method and InfoMap, yields communities that tend to be homogeneous in terms of Left/Right node composition. We also examine centrality measures and find that hyperlink-induced topic search (HITS) identifies many more hubs on the Left than on the Right. When comparing tweet content, we find that tweets about ‘Trump’ were widespread in both the Left and Right, although the accompanying language (i.e., critical on the Left, but supportive on the Right) was unsurprisingly different. Nodes with large degrees in communities on the Left include accounts that are associated with disparate areas, including activism, business, arts and entertainment, media, and politics. By contrast, support of Donald Trump was a common thread among the Right communities, connecting communities with accounts that reference white-supremacist hate symbols, communities with influential personalities in the alt-right, and the largest Right community (which includes the Twitter account FoxNews).

How the Far-Right Polarises Twitter: 'Highjacking' Hashtags in Times of COVID-19

Twitter influences political debates. Phenomena like fake news and hate speech show that political discourse on micro-blogging can become strongly polarised by algorithmic enforcement of selective perception. Some political actors actively employ strategies to facilitate polarisation on Twitter, as past contributions show, via strategies of 'hashjacking'; the use of someone else’s hashtag in order to promote one's own social media agenda. For the example of COVID-19 related hashtags and their retweet networks, we examine the case of partisan accounts of the German far-right party Alternative für Deutschland (AfD) and their potential use of 'hashjacking' in May 2020. Our findings indicate that polarisation of political party hashtags has not changed significantly in the last two years. We see that right-wing partisans are actively and effectively polarising the discourse by 'hashjacking' COVID-19 related hashtags, like #CoronaVirusDE or #FlattenTheCurve. This polarisation strategy is dominated by the activity of a limited set of heavy users. The results underline the necessity to understand the dynamics of discourse polarisation, as an active political communication strategy of the far-right, by only a handful of very active accounts.

#Opinionleaders: a comparison of self-reported and observable influence of Twitter users

ABSTRACT Social media have become forums of discussions on political and societal debates in which individual users may forward information or influence others. While prior studies either employed network analyses or surveys to identify opinion leaders and their characteristics, the present investigation combines these two approaches to address the relationship between observable and self-perceived influence. For this purpose, a retweet network of Twitter communication on the Brexit debate (N = 15,018) was analyzed in relation to a survey on motives and personality traits that was filled out by a subsample of active users (N = 98). Results showed that users’ eigenvector centrality (as a measure of influence in the network) was significantly related to their political interest and their number of followers, but not to self-perceived opinion leadership. According to a comparison of self-assessment and network position, those with stronger motivations to distribute relevant information tended to overestimate their influence in the network. Implications for the identification of opinion leaders are discussed.

Bots fired: examining social bot evidence in online mass shooting conversations

Mass shootings, like other extreme events, have long garnered public curiosity and, in turn, significant media coverage. The media framing, or topic focus, of mass shooting events typically evolves over time from details of the actual shooting to discussions of potential policy changes (e.g., gun control, mental health). Such media coverage has been historically provided through traditional media sources such as print, television, and radio, but the advent of online social networks (OSNs) has introduced a new platform for accessing, producing, and distributing information about such extreme events. The ease and convenience of OSN usage for information within society’s larger growing reliance upon digital technologies introduces potential unforeseen risks. Social bots, or automated software agents, are one such risk, as they can serve to amplify or distort potential narratives associated with extreme events such as mass shootings. In this paper, we seek to determine the prevalence and relative importance of social bots participating in OSN conversations following mass shooting events using an ensemble of quantitative techniques. Specifically, we examine a corpus of more than 46 million tweets produced by 11.7 million unique Twitter accounts within OSN conversations discussing four major mass shooting events: the 2017 Las Vegas concert shooting, the 2017 Sutherland Springs church chooting, the 2018 Parkland School Shooting and the 2018 Santa Fe school shooting. This study’s results show that social bots participate in and contribute to online mass shooting conversations in a manner that is distinguishable from human contributions. Furthermore, while social bots accounted for fewer than 1% of total corpus user contributors, social network analysis centrality measures identified many bots with significant prominence in the conversation networks, densely occupying many of the highest eigenvector and out-degree centrality measure rankings, to include 82% of the top-100 eigenvector values of the Las Vegas retweet network.

#MeToo, Networked Acknowledgment, and Connective Action: How “Empowerment Through Empathy” Launched a Social Movement

How did efforts that prompted the sharing of personal experiences of sexual violence and harassment around #MeToo coalesce into calls for action across a range of institutions and communities? We argue that sharing experiences of trauma in digital spaces created a network of acknowledgment, which supported and sustained nascent #MeToo activism based on the logic of connective action. This article attempts to (a) understand the temporal dynamics of these different discourses within the #MeToo movement on Twitter, (b) reveal the accounts animating these discourses and the most prominent themes within them, and (c) model the overtime relationship between these discourses and their relationship to major news event and #MeToo revelations. To do so, we analyze a 1% sample of tweets from the 5-month period following the revelations about Harvey Weinstein in early October 2017, employing a range of computational approaches, including part-of-speech tagging, dependency analysis, hashtags extraction, and retweet network analysis—to identify key discourses, actors, and themes. We then conduct time series analysis to identify the relationship between the two discourses and predict how the ebbs and flows of each discourse are shaped by news events.

Characterizing the Twitter network of prominent politicians and SPLC-defined hate groups in the 2016 US presidential election

We characterize the Twitter networks of the major presidential candidates, Donald J. Trump and Hillary R. Clinton, with various American hate groups defined by the US Southern Poverty Law Center (SPLC). We further examined the Twitter networks for Bernie Sanders, Ted Cruz, and Paul Ryan, for 9 weeks around the 2016 election (4 weeks prior to the election and 4 weeks post-election). We carefully account for the observed heterogeneity in the Twitter activity levels across individuals through the null hypothesis of apathetic retweeting that is formalized as a random network model based on the directed, multi-edged, self-looped, configuration model. Our data revealed via a generalized Fisher’s exact test that there were significantly many Twitter accounts linked to SPLC-defined hate groups belonging to seven ideologies (Anti-Government, Anti-Immigrant, Anti-LGBT, Anti-Muslim, Alt-Right, White-Nationalist and Neo-Nazi) and also to @realDonaldTrump relative to the accounts of the other four politicians. The exact hypothesis test uses Apache Spark’s distributed sort and join algorithms to produce independent samples in a fully scalable way from the null model. Additionally, by exploring the empirical Twitter network we found that significantly more individuals had the fewest retweet degrees of separation simultaneously from Trump and each one of these seven hateful ideologies relative to the other four politicians. We conduct this exploration via a geometric model of the observed retweet network, distributed vertex programs in Spark’s GraphX library and a visual summary through neighbor-joined population retweet ideological trees. Remarkably, less than 5% of individuals had three or fewer retweet degrees of separation simultaneously from Trump and one of several hateful ideologies relative to the other four politicians. Taken together, these findings suggest that Trump may have indeed possessed unique appeal to individuals drawn to hateful ideologies; however, such individuals constituted a small fraction of the sampled population.

Characterizing the 2016 Russian IRA influence campaign

Until recently, social media were seen to promote democratic discourse on social and political issues. However, this powerful communication ecosystem has come under scrutiny for allowing hostile actors to exploit online discussions in an attempt to manipulate public opinion. A case in point is the ongoing U.S. Congress investigation of Russian interference in the 2016 U.S. election campaign, with Russia accused of, among other things, using trolls (malicious accounts created for the purpose of manipulation) and bots (automated accounts) to spread propaganda and politically biased information. In this study, we explore the effects of this manipulation campaign, taking a closer look at users who re-shared the posts produced on Twitter by the Russian troll accounts publicly disclosed by U.S. Congress investigation. We collected a dataset of 13 million election-related posts shared on Twitter in the year of 2016 by over a million distinct users. This dataset includes accounts associated with the identified Russian trolls as well as users sharing posts in the same time period on a variety of topics around the 2016 elections. We use label propagation to infer the users’ ideology based on the news sources they share. We are able to classify a large number of the users as liberal or conservative with precision and recall above 84%. Conservative users who retweet Russian trolls produced significantly more tweets than liberal ones, about 8 times as many in terms of tweets. Additionally, trolls’ position in the retweet network is stable overtime, unlike users who retweet them who form the core of the election-related retweet network by the end of 2016. Using state-of-the-art bot detection techniques, we estimate that about 5% and 11% of liberal and conservative users are bots, respectively. Text analysis on the content shared by trolls reveal that conservative trolls talk about refugees, terrorism, and Islam, while liberal trolls talk more about school shootings and the police. Although an ideologically broad swath of Twitter users were exposed to Russian trolls in the period leading up to the 2016 U.S. Presidential election, it is mainly conservatives who help amplify their message.

An Agent-Based Model for Information Diffusion over Online Social Networks

Online social networks have become a new channel for urban citizens to acquire information. The efficient information diffusion in their communities ensures wide awareness of updated special events. With agent-based models built on the NetLogo platform, I study information diffusion on online social networks with different simulated network structures. Outcomes from simulated networks and from a case study of real-world Twitter networks show that there exist a range of paired optimal propagation parameters that could mimic real-world information diffusion. It is found that the physical space and the process of information diffusion on the real retweet network over time still demonstrate a geographic pattern showing that a local city or a related city is more involved in a special event in the area.

Examining Emergent Communities and Social Bots Within the Polarized Online Vaccination Debate in Twitter

Many states in the United States allow a “belief exemption” for measles, mumps, and rubella (MMR) vaccines. People’s opinion on whether or not to take the vaccine can have direct consequences in public health. Social media has been one of the dominant communication channels for people to express their opinions of vaccination. Despite governmental organizations’ efforts of disseminating information of vaccination benefits, anti-vaccine sentiment is still gaining momentum. Studies have shown that bots on social media (i.e., social bots) can influence opinion trends by posting a substantial number of automated messages. The research presented here investigates the communication patterns of anti- and pro-vaccine users and the role of bots in Twitter by studying a retweet network related to MMR vaccine after the 2015 California Disneyland measles outbreak. We first classified the users into anti-vaccination, neutral to vaccination, and pro-vaccination groups using supervised machine learning. We discovered that pro- and anti-vaccine users retweet predominantly from their own opinion group. In addition, our bot analysis discovers that 1.45% of the corpus users were identified as likely bots which produced 4.59% of all tweets within our dataset. We further found that bots display hyper-social tendencies by initiating retweets at higher frequencies with users within the same opinion group. The article concludes that highly clustered anti-vaccine Twitter users make it difficult for health organizations to penetrate and counter opinionated information while social bots may be deepening this trend. We believe that these findings can be useful in developing strategies for health communication of vaccination.

Interactive Behavior in Political Discussions on Twitter: Politicians, Media, and Citizens’ Patterns of Interaction in the 2015 and 2016 Electoral Campaigns in Spain

Twitter has become a privileged data source for analyzing the behavior of users when interacting online. This research aims to explore the interactive behavior of users in political discussions and the changes in their behavior over time. Understanding the interactive functions of Twitter (retweeting, mentioning, and replying) as digital traces of users’ behavior, we analyze the patterns of interaction of politicians, media, and citizens in two political discussions in Spain during the 2015 and 2016 general elections. Our results confirm previous studies that prove the homophilic behavior of politicians and citizens in political discussions. The networks of interaction, in particular, the retweet network, resemble echo chambers. It also shows that media play the role of weak ties of the networks. The analysis also shows that the patterns of interaction remained stable after the repetition of the election, and only a meager part of the users participating in both discussions changed their behavior. This article aims to contribute to the use of Twitter as a source for understanding people’s interactions is political discussions in social media and their dynamics across time.

Twitter use in scientific communication revealed by visualization of information spreading by influencers within half a year after the Fukushima Daiichi nuclear power plant accident.

Scientific communication through social media, particularly Twitter has been gaining importance in recent years. As such, it is critical to understand how information is transmitted and dispersed through outlets such as Twitter, particularly in emergency situations where there is an urgent need to relay scientific information. The purpose of this study is to examine how original tweets and retweets on Twitter were used to diffuse radiation related information after the Fukushima Daiichi nuclear power plant accident. Out of the Twitter database, we purchased all tweets (including replies) and retweets related to Fukushima Daiichi nuclear power plant accident and or radiation sent from March 2nd, 2011 to September 15th, 2011. This time frame represents the first six months after the East Japan earthquake, which occurred on March 11th, 2011. Using the obtained data, we examined the number of tweets and retweets and found that only a small number of Twitter users were the source of the original posts that were retweeted during the study period. We have termed these specific accounts as “influencers”. We identified the top 100 influencers and classified the contents of their tweets into 3 groups by analyzing the document vectors of the text. Then, we examined the number of retweets for each of the 3 groups of influencers, and created a retweet network diagram to assess how the contents of their tweets were being spread. The keyword “radiation” was mentioned in over 24 million tweets and retweets during the study period. Retweets accounted for roughly half (49.7%) of this number, and the top 2% of Twitter accounts defined as “influencers” were the source of the original posts that accounted for 80.3% of the total retweets. The majority of the top 100 influencers had individual Twitter accounts bearing real names. While retweets were intensively diffused within a fixed population, especially within the same groups with similar document vectors, a group of influencers accounted for the majority of retweets one month after the disaster, and the share of each group did not change even after proven scientific information became more available.