Over the period of analysis from December 15th, 2018 to January 20th, 2019, Alto’s data science team analyzed the German political and social debate. Public data analyzed includes 2,960,000 total results from 283,517 unique authors, 203,658 conversations, and 281,061 unique pieces of content shared across multiple digital sources such as Twitter, Facebook, YouTube, Instagram, blogs, forums, and other digital communities. Results in the German language and results geolocated in Germany were collected. Alto’s analysis focuses on understanding the role and digital influence of politicians, civil society, and social and digital media platforms in shaping the public online debate in Germany.
Alto’s data analysts conducted an additional analysis of explicit mentions on all of the indexed sources previously described over an extended period of December 15th to March 15th. In this analysis, we measured explicit mentions of political parties and politicians, finding that 31.6% of mentions refer to the AfD or associated politicians, 22.9% to the CDU or associated politicians, 21.9% to the SPD or associated politicians, 6.98% to Die Grüne or associated politicians, 6.7% to the FDP or associated politicians, 5.9% to the CSU or associated politicians, and 4% to Die Linke or associated politicians.
By analyzing the top 200 keywords & hashtags representing 98% of the total results analyzed, Alto’s analysts identified the following narratives in the public digital sociopolitical debate:
- Nazi Raus movement (33.8%): Discourse surrounding the Nazi Raus or “Nazis Out” movement with several mentions of the AfD as a focal point of opposition of this movement
- European elections agenda (19.5%): Conversations on both German policies, politicians, and parties such as the CSU, SPD, CSU, Merkel, or the Greens influencing the policy agenda
- European asylum policy discussions (17.8%): Discussion on matters such as the UN Migration Pact or the NGO Sea Watch, highlighting Europe’s stance towards immigration
- Muslims in Europe (9.6%): Discourse on the “islamization” of Europe, including xenophobic commentary that ties into the broader immigration conversation
- Immigration and Violence (5.5%) Conversations tying immigration and Islam to a rise in violence and lack of security in Germany
- Debate on German public media license fee (4.8%): Conversations rebuking the new media license fee for TV and radio implemented in Germany
- Environmental protection (4.1%): Conversations on matters related to climate change and ecological policies, many of which are advocated for by the Greens
Alto data scientists used Alto Analyzer, Alto’s proprietary cloud-based analytics platform, to build and identify the largest communities of users interacting in connection with the German public debate. This community was identified in Twitter, and their interactions were filtered for re-tweets only, in order to perform a topological analysis of the propagation of messages. This resulted in a unimodal network of authors (giant component, edges being re-tweets). To determine the different communities and visually represent the resulting network, Alto’s data scientists applied clustering algorithms, like the Louvain Method for community detection, for example. The graph is visualized as shown below with a total of 108,333 users and 1,980,049 retweets. Five key communities emerged out of the community detection analysis:
Network topology is characterized by network structures with nodes (profiles) and edges (lines) which connect them. Alto’s algorithm clusters nodes and edges in order to calculate proximities and communities of users.
- Nazi Raus Movement and AfD Critics (61% of users, 40% of retweets): Support for the Nazi Raus movement and criticisms against the AfD and their stances on immigration
- European Elections Agenda (17% of users, 7% of retweets): Discussions on the future of the EU and the influence of the German politics in the elections, highlighting several domestic parties
- AFD Supporters and Anti- Immigration (16% of users, 50% of retweets): Support for the policies of the AfD and anti-immigrant sentiment characterize this community
- Current International Affairs (4% of users, 2% of retweets): Current international affairs such as Brexit and the Yellow Vests, as driven by several international media
- Piraten Partei and European Elections (2% of users, 1% of retweets): Piraten Partei discourse and advocacy for the party’s policies
Politicians Among the Top Communities
In an analysis of influential nodes in the communities mapped, Alto measured influence mathematically based on the structural connections of the authors in the digital debate and their ability to propagate messages to larger audiences in the network (centrality measurement), showing that 16 verified political accounts from the CDU and 15 verified political accounts from the SPD appeared in the EU Elections Agenda community. Politicians from the other main parties were involved in the debate in lesser numbers.
Abnormality detection – Most Active Users
To determine if users demonstrating abnormal levels of activity were present in the debate, Alto’s team focused on an analysis of outliers and their frequency of posting. The results indicated that the 1,226 most active users generated, on average, 594 comments throughout the period of analysis. Applying a standard deviation of 482, this means that users with more than 1,076 comments are considered outliers. Following this, we can identify 106 users (0.09 % of all users) demonstrating abnormal activity. This means that over the period of analysis, each abnormal activity user produced at least 29 posts per day resulting in a total of 189,148 (9.55%) total posts.
48.19% of users are geolocated in Germany, and 47.17% of users do not publicly express their geolocation. Users posting in German from other locations include Switzerland (0.73%), Austria (0.61%), and the United States (0.44%).
Role of Traditional, Emerging, and Foreign Media in the Debate
To determine which media sites are most influential, Alto’s algorithms take into account the number of users and the volume and frequency of links from media sites being shared across social media sources to calculate how influential the site is within the context of the analysis. Alto’s software ranks content influence similar to Google’s algorithms for web page ranking – the content from more relevant sites are likely to receive greater attention from more users over a sustained period of time.
Alto’s analysis found that traditional German media and social media platforms ranked high in influence, as did a growing network of emerging digital media with highly specific editorial positions. Please see the table below for the top 150 most influential domains and the contribution of each community to the propagation of each domain’s content within the network.
Some of the key findings are:
– The AfD Supporters community has a high level of affinity to several sites which rank among the top most relevant domains and are shared only marginally by other communities identified in the analysis. Some examples of these sites, as can be viewed in the tables below, are journalistenwatch.com (99..40%, AfD), bild.de (92.07%, AfD), focus.de (80.31%), tichyseinblick.de (96.63%, AfD), epochtimes.de (98.54%, AfD), jungefreiheit.de (98.61%, AfD), philosophia-perennis.com (99.10%, AfD), pi-news.net (99.19%, AfD), ffd365.de (99.91%, AfD), anonymousnews.ru (98.87%, AfD), all appearing among the top 25 most relevant domains in the study.
– 13 of the top 25 domains are shared at a rate of over 80% by the AfD Supporters community.
– Facebook (82.62%, AfD) and YouTube (70.09%, AfD) are both frequently shared by identities within the AfD community and are highly influential within these networks.
– Russia Today (RT or rt.com) and Sputnik (sputniknews.com) appear among the most shared domains in the debate at 46th and 69th, respectively. RT is shared with a frequency of 83.51% and Sputnik was shared at a rate of 88.5% by the AfD Supporters community. This signals the presence of Russian media in the German socio-political debate on Twitter.
Top 150 Domains – Percentage of Times Each Domain Is Shared per Community
Interested in our work? Please contact us at firstname.lastname@example.org. To learn more about Alto Data Analytics, subscribe to our newsletter below.