scholarly journals Political relevance in the eye of the beholder: Determining the substantiveness of TV shows and political debates with Twitter data

First Monday ◽  
2017 ◽  
Vol 22 (4) ◽  
Author(s):  
Mark Boukes ◽  
Damian Trilling
Keyword(s):  
Social Media ◽  
Talk Shows ◽  
The Political ◽  
Television Programs ◽  
Political Debates ◽  
Twitter Data ◽  
Genre Classification ◽  
Audience Responses ◽  
Tv Shows

Addressing the call to move beyond a simple genre classification of TV shows as either substantive (hard) news or non-substantive (soft) infotainment, we propose using social media reactions to determine a program’s political relevance. Such an approach provides information that goes beyond genre or content characteristics and reflects what really reaches an audience. Analyzing tweets about two Dutch talk shows and four U.S. primary debates, we show that audience responses to television programs differ considerably regarding their political relevance. Thereby, we demonstrate how examining online audience reactions can be employed as a sophisticated and valid way to assess the political relevance of TV programs.

scholarly journals Facebook – selvfremstilling, small talk og social regulering

2012 ◽  
Vol 28 (52) ◽  
pp. 21 ◽  
Author(s):  
Anne Scott Sørensen
Keyword(s):  
Social Media ◽  
Qualitative Study ◽  
Speech Acts ◽  
Social Regulation ◽  
Personal Networks ◽  
Survey Study ◽  
Small Talk ◽  
Genre Classification ◽  
The Status

<p>In this paper, I will document the use of Facebook in a Danish context, taking a mediatisation perspective focused on the network sociality in question (Jensen, 2009; Tække, 2010a/b) and the communication (Miller, 2008) of social media. This discussion is based on a qualitative study from 2010, consisting of participants recruited from a survey study. The study explores three dilemmas resulting from network media’s communicative paradox, involving the premises of self-representation, use of status updates, and social regulation. These dilemmas are contextualised by recent theories of genre and speech-acts (Miller, 2004; Butler, 2005) as well as by existing studies of related issues, such as the composition of personal networks (friend lists) and the degree to which personal profiles are open and accessible (privacy). While the study generally confirms recent research in these fields, such research has not previously been documented (or refined) in a Danish context. The paper’s most important contributions, however, consist of its identification of the three communicative dilemmas, its tentative genre classification of the status update, and its discussion of implicit social regulation and ethics, which have not been previously been considered.</p>

Deep Learning Method for Prediction of DDoS Attacks on Social Media

2019 ◽  
Vol 11 (01n02) ◽  
pp. 1950002
Author(s):  
Rasim M. Alguliyev ◽  
Ramiz M. Aliguliyev ◽  
Fargana J. Abdullayeva
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Social Networking ◽  
Cyber Attacks ◽  
Test Accuracy ◽  
Learning Method ◽  
Ddos Attacks ◽  
Twitter Data ◽  
Social Events

Recently, data collected from social media enable to analyze social events and make predictions about real events, based on the analysis of sentiments and opinions of users. Most cyber-attacks are carried out by hackers on the basis of discussions on social media. This paper proposes the method that predicts DDoS attacks occurrence by finding relevant texts in social media. To perform high-precision classification of texts to positive and negative classes, the CNN model with 13 layers and improved LSTM method are used. In order to predict the occurrence of the DDoS attacks in the next day, the negative and positive sentiments in social networking texts are used. To evaluate the efficiency of the proposed method experiments were conducted on Twitter data. The proposed method achieved a recall, precision, [Formula: see text]-measure, training loss, training accuracy, testing loss, and test accuracy of 0.85, 0.89, 0.87, 0.09, 0.78, 0.13, and 0.77, respectively.

Polarization of COVID-19 Vaccine Discourse on Twitter: Implications for Vaccine Policy (Preprint)

2021 ◽  
Author(s):  
Loni Hagen ◽  
Ashley Fox ◽  
Heather O'Leary ◽  
Deaundre Dyson ◽  
Kimberly Walker ◽  
...  
Keyword(s):  
Social Media ◽  
General Population ◽  
Adult Population ◽  
The Political ◽  
Connected Group ◽  
Twitter Data ◽  
Political Advantage ◽  
Social Media Presence ◽  
Political Right ◽  
Roll Out

UNSTRUCTURED Since COVID-19 vaccines became broadly available to the adult population, sharp divergences in uptake have emerged along partisan lines. Researchers have pointed to a polarized social media presence contributing to the spread of mis-/dis-information as being responsible for these growing partisan gaps in uptake. The major aim of this study was to identify and describe influential actors, topics, behaviors, and community structures related to COVID-19 vaccine conversations on Twitter prior to the vaccine roll-out to the general population and discuss implications for vaccine promotion and policy. Using Twitter data on COVID-19 vaccination during July 2020, we found that Twitter vaccine conversations were highly polarized with different actors occupying separate “clusters.” The anti-vaccine cluster was the most densely connected group. Among the 100 most influential actors, medical experts are outnumbered both by partisan actors and by activist vaccine skeptics/conspiracy theorists. Scientists and medical actors were largely absent from the conservative network, and anti-vaccine sentiment was especially salient among actors on the political right. Conversations related to COVID-19 vaccines are highly polarized along partisan lines with “trust” in vaccines being manipulated to the political advantage of partisan actors.

scholarly journals Social media as a political backchannel

2014 ◽  
Vol 66 (3) ◽  
pp. 313-328 ◽  
Author(s):  
Bente Kalsnes ◽  
Arne H. Krumsvik ◽  
Tanja Storsul
Keyword(s):  
Social Media ◽  
Audience Participation ◽  
Analysis Model ◽  
Media Criticism ◽  
Content Type ◽  
Agenda Setter ◽  
Political Debates ◽  
Critical Scrutiny ◽  
Tv Shows ◽  
Televised Debates

Purpose – The purpose of this paper is to explore how Twitter is used as a political backchannel and potential agenda setter during two televised political debates during the Norwegian election in 2011. The paper engages with current debates about the role of social media in audience participation and traditional media's changing role as gatekeepers and agenda setter. Design/methodology/approach – A combination of quantitative and qualitative methods. By introducing and using the IMSC multiple step analysis model on the Twitter datasets, the authors are able to analyse the flow of thousands of tweets and compare them with topics discussed in the televised debates. Findings – The paper finds that the same topics are discussed on Twitter as on TV, but “the debate about the debate” or Meta talk tweets reveal critical scrutiny of the agenda. The paper identifies a clear pattern of political fandom and media criticism in the “debate about the debate”, indicating that Meta talk in social media can function as a critical public sphere, also in real time, which has not been identified in existing studies of Twitter and political TV shows. Originality/value – The analysis is unique in the sense that the paper analyses a smaller, national Twitter population in deeper detail than what is common in larger Twitter studies related to political televised debates. The IMSC model can be used in future Twitter studies to uncover layers in the data material and structure the findings.

scholarly journals How Many People Live in Political Bubbles on Social Media? Evidence From Linked Survey and Twitter Data

SAGE Open ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 215824401983270 ◽  
Author(s):  
Gregory Eady ◽  
Jonathan Nagler ◽  
Andy Guess ◽  
Jan Zilinsky ◽  
Joshua A. Tucker
Keyword(s):  
Social Media ◽  
Online News ◽  
Political Information ◽  
The Political ◽  
The Internet ◽  
Representative Survey ◽  
Twitter Data ◽  
Social Media Platforms ◽  
Media Environments ◽  
Political Spectrum

A major point of debate in the study of the Internet and politics is the extent to which social media platforms encourage citizens to inhabit online “bubbles” or “echo chambers,” exposed primarily to ideologically congenial political information. To investigate this question, we link a representative survey of Americans with data from respondents’ public Twitter accounts ( N = 1,496). We then quantify the ideological distributions of users’ online political and media environments by merging validated estimates of user ideology with the full set of accounts followed by our survey respondents ( N = 642,345) and the available tweets posted by those accounts ( N ~ 1.2 billion). We study the extent to which liberals and conservatives encounter counter-attitudinal messages in two distinct ways: (a) by the accounts they follow and (b) by the tweets they receive from those accounts, either directly or indirectly (via retweets). More than a third of respondents do not follow any media sources, but among those who do, we find a substantial amount of overlap (51%) in the ideological distributions of accounts followed by users on opposite ends of the political spectrum. At the same time, however, we find asymmetries in individuals’ willingness to venture into cross-cutting spaces, with conservatives more likely to follow media and political accounts classified as left-leaning than the reverse. Finally, we argue that such choices are likely tempered by online news watching behavior.

‘Cheap Talk’? Second screening and the irrelevance of TV political debates

Journalism ◽  
2019 ◽  
Vol 20 (8) ◽  
pp. 1108-1123 ◽  
Author(s):  
Andrea Ceron ◽  
Sergio Splendore
Keyword(s):  
Social Media ◽  
General Public ◽  
Inverse Relationship ◽  
Talk Shows ◽  
Political Debates ◽  
Electoral Campaign ◽  
Social Tv ◽  
Political Talk ◽  
Twitter Users ◽  
Online Debate

This article analyzes 3 months of online debate during the electoral campaign for the 2016 Italian constitutional referendum. Through supervised sentiment analysis, we assess the extent of support for the referendum within the general public of Twitter users ( Twittersphere) by analyzing the voting intentions expressed online in 2,369,333 tweets. Similarly, we exploit the practice of social TV and investigate the support for the referendum expressed by the 160,465 tweets posted by second screeners, that is, the subsample of Twitter users who watched and actively commented on nine political talk shows during the campaign. We compare the mentions and the attitudes of the Twittersphere and the second screeners by means of a lead–lag analysis to test whether the second screeners can act as influencers and trendsetters able to shape or anticipate attention and opinions toward an issue within larger audiences. The results reveal an inverse relationship between the Twittersphere and the second screeners whereby the reactions of the latter diverge from those of the general Twitter public. This finding has implications for the literature on echo chambers and the polarization of social media.

Topics and emotions in Russian Twitter propaganda

First Monday ◽  
2019 ◽  
Author(s):  
Daniel Taninecz Miller
Keyword(s):  
Social Media ◽  
Political Communication ◽  
Close Association ◽  
Temporal Association ◽  
The Political ◽  
Media Discourse ◽  
Black And White ◽  
Twitter Data ◽  
Consistent Manner ◽  
Political Spectrum

The increasing importance of social media to political communication means the study of government-sponsored social media activity deserves further exploration. In particular, text-as-data techniques like topic models and emotional lexicons provide potential for new types of content analysis of large collections of government-backed social media discourse. Applying text-as-data methods to a corpus of Russian-sponsored Twitter data generated before, during and after the 2016 U.S. presidential election shows tweets containing a diverse set of policy-related topics as well as levels of angry and fearful emotional language that peaks in close association to the election. Text-as-data techniques show Russian sponsored tweets mentioned candidate Clinton overwhelmingly negatively and referenced candidate Trump in a positive but less consistent manner. The tweets contained large minorities of apolitical topics, and also saw higher levels of conservative hashtags than progressive ones. Topics within the tweet data show a contradictory set of topics on all “sides” of the political spectrum alongside increases in fearful and angry language in temporal association with the U.S. election. The findings of this inquiry provide evidence that the tweets were sent to heighten existing tensions through topically heterogeneous propaganda. They also caution against an overly black and white interpretation of Russian disinformation efforts online.

scholarly journals Mediatized Child Characters

2018 ◽  
Vol 1 (3) ◽  
pp. 98
Author(s):  
Elif Gizem Ugurlu
Keyword(s):  
Social Media ◽  
Child Labor ◽  
The Other ◽  
Television Series ◽  
Television Programs ◽  
Child Characters ◽  
Other Hand ◽  
The Media ◽  
Tv Shows

Child actors and actresses perform in television programs, such as contests, shows and series, and in movies broadcasted in Turkey. After the program is broadcasted, social media accounts such as Facebook and instagram are opened by their parents for these children and it is attempted to increase their popularity. Children with increased popularity begin to act in new series and advertisements, and they are drawn into a consumption cycle. While these children, who are used for humour, promotional or dramatic factors, are disturbed, on the other hand, they cause that children's real and big problems (poverty, child labor, abuse, abduction, refugee, etc.) are ignored. This study provides a perspective on child characters in competition programs, TV shows, television series, television programs and movies broadcasted on televisions in 2018 in Turkey. The program in which children aged between 5 and 12 years appear, and their Instagram accounts were tracked and examined. The culture of benefiting from the child in the media multiplies itself as the use of children as mediatic characters in the media in Turkey continues, and the fact that children can be used as a source of income without considering that they can be overwhelmed by the burden of fame becomes widespread. This indicates the perception of childhood in society, the visibility of child individuals' problems, and a frightening future for children.

scholarly journals Genre Classification of Telugu and English Movie Based on the Hierarchical Attention Neural Network

2021 ◽  
Vol 14 (1) ◽  
pp. 54-62
Author(s):  
Kumar Govindaswamy ◽  
◽  
Shriram Ragunathan ◽  
Keyword(s):  
Neural Network ◽  
Recommendation System ◽  
Short Term Memory ◽  
Hierarchical Structures ◽  
Relevant Information ◽  
Twitter Data ◽  
Genre Classification ◽  
The Social ◽  
Audio Data

Genre Classification of movies is useful in the movie recommendation system for video streaming applications like Amazon, Netflix, etc. The existing methods used either video or audio data as input that requires more computation resources to process the data for the genre classification of movies. In this study, the Hierarchical Attention Neural Network (HANN) is proposed for genre classification of movies based on the social media called Twitter data as input. Twitter data related to the Telugu and English movies are collected and applied to HANN for movie’s genre classification. IMDB data are used to evaluate the performance of the proposed HANN method. The hierarchical structures of the twitter data is considered by the proposed HANN method and the most important words related to genre classification is identified by the attention mechanism, where the other neural networks such as Artificial Neural Network and Convolutional Neural Network (CNN) returns only the important weights resulting from previous words. The HANN method has the advantages of encoding the relevant information that helps to improve the performance of the recommendation system. The experimental results show that the HANN method achieve higher performance compared to other classifiers Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM). The HANN method achieves accuracy of 73.15% in classification, while the existing BiLSTM method achieve the accuracy of 68% in classification.

Sign in / Sign up

Export Citation Format

Share Document