Election campaigning on social media: Politicians, audiences and the mediation of political communication on Facebook and Twitter (1801.08825v1)

Abstract: Although considerable research has concentrated on online campaigning, it is still unclear how politicians use different social media platforms in political communication. Focusing on the German federal election campaign 2013, this article investigates whether election candidates address the topics most important to the mass audience and to which extent their communication is shaped by the characteristics of Facebook and Twitter. Based on open-ended responses from a representative survey conducted during the election campaign, we train a human-interpretable Bayesian LLM to identify political topics. Applying the model to social media messages of candidates and their direct audiences, we find that both prioritize different topics than the mass audience. The analysis also shows that politicians use Facebook and Twitter for different purposes. We relate the various findings to the mediation of political communication on social media induced by the particular characteristics of audiences and sociotechnical environments.

• The paper shows that politicians strategically use Facebook for campaign mobilization and Twitter for real-time political commentary.
• It employs a semi-supervised, nonparametric Bayesian language model to uncover nuanced political topics from social media data.
• The study reveals a divergence between candidates' and mass audiences' topic priorities, underscoring the mediating role of platform-specific features.

An Examination of Political Campaigning on Social Media: Insights from the German Federal Election of 2013

The paper under consideration explores how politicians utilize social media platforms, specifically Facebook and Twitter, during election campaigns, focusing on the German federal election of 2013. The authors, Sebastian Stier et al., conduct an intricate analysis of the interplay between political candidates, their audiences, and the broader mass audience, using advanced quantitative text analysis methods. This paper contributes to the literature on political communication by highlighting how these different groups prioritize political topics and the roles of Facebook and Twitter in shaping political dialogue.

Methodology and Analytical Approach

The methodology employed centers on a human-interpretable Bayesian LLM applied to social media data of political candidates and their audiences. The model is uniquely crafted to identify political topics from text data, distinguishing between known topics derived from survey responses and new ones specific to the social media domain. By utilizing a semi-supervised, nonparametric Bayesian approach, the authors manage to capture the complex dynamics of political communication on social media, allowing for the emergence of additional topics not captured by traditional survey data.

Key Findings

1. Platform-Specific Use of Social Media: The paper finds that politicians employ Facebook and Twitter differently, reflective of the platforms' distinct architectures and audience characteristics. Whereas Facebook tends to be used for campaign-related activities aimed at mobilizing support and promoting events, Twitter is more frequently utilized for commenting on contemporary political events and engaging with topics of immediate public consciousness. This suggests that politicians are adeptly tailoring their communication strategies to leverage the unique affordances of these platforms.
2. Divergence from Mass Audience Priorities: The analysis reveals a divergence between the topics prioritized by political candidates and their social media audiences compared to the broader mass audience. While mass audiences prioritize core policy areas such as labor market and social policy, political discourse on social media platforms is often centered around campaign-specific and media-driven topics. This divergence underscores a fragmentation in political communication driven by the nuanced interactions specific to social media environments.
3. Implications of Sociotechnical Mediation: The paper posits that social media platforms mediate political communication through their sociotechnical characteristics, influencing how politicians craft their messages and engage with their audiences. This mediation effect prompts a shift in how political communication is conducted compared to more traditional forms of media, suggesting an evolution in campaign strategies to address more segmented audiences.

Implications and Future Research

The findings have significant implications for both practical and theoretical elements of political communication:

• Practical Implications: Understanding the distinct uses of Facebook and Twitter can help political campaigners optimize strategies for message dissemination and voter engagement. It reassures campaign strategists that a tailored, platform-specific approach is necessitated by the nuanced audience engagement each social media site engenders.
• Theoretical Implications: The paper expands on existing models of political communication by integrating cross-media analysis, thus enriching the understanding of modern campaign strategies that must adapt to interactive and segmented audiences.

Looking to the future, further research could investigate longitudinal changes in social media use in political campaigns, assess the impact of sociotechnical mediation across different political systems, or extend this analysis to non-election periods to capture variations in social media engagement.

In conclusion, this paper provides an insightful analysis into the relationship between social media and political communication, using a rigorous methodological framework to elucidate how digital platforms shape the discourse of political campaigns, reflecting broader shifts in the political communication landscape.