Echo Chamber or Public Sphere? Predicting Political Orientation and Measuring Political Homophily in Twitter Using Big Data

Colleoni, Elanor; Rozza, Alessandro; Arvidsson, Adam

doi:10.1111/jcom.12084

Cited by 930 publications

(669 citation statements)

References 34 publications

Supporting

Mentioning

606

Contrasting

Unclassified

Order By: Relevance

“…For same-sex marriage, however, the interaction did not approach statistical significance, although the effect remained in the same direction (IRR = 1.10, P = 0.746, 95% CI = 0.61, 1.98). These findings indicate there may be an in-group advantage (22,33) for moral contagion; that is, moral-emotional language may spread more widely within in-group networks than out-group networks (for a visualization of the retweet network for messages containing moral and emotional language, see Fig. 3).…”

Section: Resultsmentioning

confidence: 99%

Emotion shapes the diffusion of moralized content in social networks

Brady

Wills

Jost

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

806

605

View full text Add to dashboard Cite

Political debate concerning moralized issues is increasingly common in online social networks. However, moral psychology has yet to incorporate the study of social networks to investigate processes by which some moral ideas spread more rapidly or broadly than others. Here, we show that the expression of moral emotion is key for the spread of moral and political ideas in online social networks, a process we call "moral contagion." Using a large sample of social media communications about three polarizing moral/political issues (n = 563,312), we observed that the presence of moral-emotional words in messages increased their diffusion by a factor of 20% for each additional word. Furthermore, we found that moral contagion was bounded by group membership; moral-emotional language increased diffusion more strongly within liberal and conservative networks, and less between them. Our results highlight the importance of emotion in the social transmission of moral ideas and also demonstrate the utility of social network methods for studying morality. These findings offer insights into how people are exposed to moral and political ideas through social networks, thus expanding models of social influence and group polarization as people become increasingly immersed in social media networks.O ur sense of right and wrong shapes our daily interactions in a variety of domains such as political participation, consumer choices, and close relationships. What factors inform our intuitions about morality? Influential theories in psychology maintain that our moral sense is shaped by the social world (1), insofar as decades of research demonstrate that social communities influence moral development in children (2) and account for cross-cultural variation in moral beliefs (3). Furthermore, social information serves as input for cognitive and emotional processes in moral judgment and decision-making (4).Despite a broad consensus that morality is influenced by attitudes and norms transmitted by our social world, remarkably little work has examined how social networks transmit moral attitudes and norms. Most existing research takes a dyadic perspective to study the social transmission of morality; typically, one person (such as a child) is exposed to another's ideas (e.g., parent) through behavior or communication (1, 2). In society, the transmission of morality goes well beyond the dyad. Our moods, thoughts, and actions are shaped by the entire network of individuals with whom we share direct and indirect relationships (5). Thus, we often develop similar ideas and intuitions as others because we are socially connected to them (6). This phenomenon is often deemed social "contagion" because it mimics the spread of disease. We use a social contagion perspective to illuminate how morally tinged messages about political issues are transmitted through social networks.Research on the emotional underpinnings of morality provides a theoretical framework to understand the processes that may drive social contagion in the domain of morality. Emotions...

show abstract

Section: Resultsmentioning

confidence: 99%

Emotion shapes the diffusion of moralized content in social networks

Brady

Wills

Jost

et al. 2017

Proc. Natl. Acad. Sci. U.S.A.

806

605

View full text Add to dashboard Cite

show abstract

“…For example, the global Internet is centralized in a few economically and politically dominating nations (Park et al, 2011;Ruiz & Barnett, 2014). Similarly, Facebook friendships and Twitter followings display homophily along similar cultural and socioeconomic attributes-similar patterns are also manifested in the offline world (Barnett & Benefield, 2015;Colleoni, Rozza, & Arvidsson, 2014).…”

Section: Rq5mentioning

confidence: 99%

Measuring international relations in social media conversations

Barnett

Chu

et al. 2017

Government Information Quarterly

View full text Add to dashboard Cite

a b s t r a c t a r t i c l e i n f oThis paper examines international relations as perceived by the public in their social media conversations. It examines over 1.8 billion Facebook postings in English and 51 million Chinese posts on Weibo, to reveal the relations among nations as expressed in social media conversations. It argues that social media represent a transnational electronic public sphere, in which public discussions reveal characteristics of international relations as perceived by a foreign public. The findings show that the international relations in social media postings match the core-peripheral structure proposed in the World Systems Theory. Additionally, the relations are associated with the amount of news coverage and public attention a country receives. Overall, the study demonstrates the value of webometric data in revealing how international relations are perceived by average citizens.

show abstract

“…The main distinctions of several of these models with DMT-Demographic models are that (a) most previous literature use only tweet content analysis to predict demographic information (Nguyen et al, 2013) while our model leverages different modals of user information including profile picture, (b) though some of the works use interesting network information they do not leverage other user details as potential signals (Colleoni et al, 2014;Culotta et al, 2015), (c) many of the models involve a lot of feature engineering like extracting location indicative words for geolocation prediction, etc. (Han et al, 2014;Sloan et al, 2015), (d) our model learns shared and task-specific layer parameters as we handle the demographic prediction Table 3: Task-specific Macro F1-score for different DMT-Demographic models.…”

Section: Related Workmentioning

confidence: 99%

Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning

Vijayaraghavan¹,

Vosoughi²,

Roy³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

Twitter should be an ideal place to get a fresh read on how different issues are playing with the public, one that's potentially more reflective of democracy in this new media age than traditional polls. Pollsters typically ask people a fixed set of questions, while in social media people use their own voices to speak about whatever is on their minds. However, the demographic distribution of users on Twitter is not representative of the general population. In this paper, we present a demographic classifier for gender, age, political orientation and location on Twitter. We collected and curated a robust Twitter demographic dataset for this task. Our classifier uses a deep multi-modal multitask learning architecture to reach a stateof-the-art performance, achieving an F1-score of 0.89, 0.82, 0.86, and 0.68 for gender, age, political orientation, and location respectively.

show abstract

Echo Chamber or Public Sphere? Predicting Political Orientation and Measuring Political Homophily in Twitter Using Big Data

Cited by 930 publications

References 34 publications

Emotion shapes the diffusion of moralized content in social networks

Emotion shapes the diffusion of moralized content in social networks

Measuring international relations in social media conversations

Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning

Contact Info

Product

Resources

About