Poland: Digital Public Debate Ahead of EU Parliamentary Elections

The public assassination of Mayor of Gdansk, Pawel Adamowicz, and the subsequent national mourning served as a central point of debate and disagreement between the main parties, PO and PiS.

Over the period of analysis from December 15th, 2018 to January 20th, 2019, Constella’s data science team analyzed the Polish political and social debate. Public data analyzed include 1,407,073 total results from 106,856 unique authors, 84,737 conversations, and 98,191 unique pieces of content shared across multiple digital sources such as Twitter, Facebook, YouTube, Instagram, blogs, forums, and other digital communities. Both results generated in the Polish language and results geolocated in Poland were collected. Constella’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 Poland.

A central narrative of the debate revolved around the murder of Pawel Adamowicz, who on January 13th was fatally stabbed on stage during a live charity event in Gdansk, where he had served as Mayor for 20 years. The national mourning following this event served as a dominant narrative of discussion through which political parties and commentators in the debate took the opportunity to engage in criticisms regarding the socio-political climate in Poland. Other conversations focused on policy related to environmental issues and secularism, for example, although the conversation was heavily focused on polarizing criticisms among both larger and emerging political parties in PO, PiS, and the Eurosceptics camp – many of which stemmed from the event of Mayor Adamowicz’s murder.

Narratives Analysis

By analyzing the top 300 keywords & hashtags representing 98.6% of the total results analyzed, Constella’s analysts identified the following narratives in the public digital sociopolitical debate.

  1. Criticism of PiS and PO: Disappointment with the politics of PiS and PO and continuous conflict between both parties. (50.53 % of users)
  2. National mourning: National mourning but also vivid and emotional narration about the motives and consequences of the Gdansk Mayor’s murder (23.32% of users)
  3. Criticism of PO: PiS criticizing the PO’s new approach the governing of Warsaw’s city hall. Concern about complaints and slander arising during the Middle East security conference organized in Warsaw (15.9% of users)
  4. 100th anniversary of the victorious Polish insurrection against Prussia (7.42% of users)
  5. Criticism of EU: Criticism of a new EU initiative on the financing of non-governmental organizations and also its dependence on the EU. Criticism of PiS politics (2.83% of users)

Communities Analysis

Constella data scientists used Analyzer, Constella’s proprietary cloud-based analytics platform, to build and identify the largest communities of users interacting in connection with the French 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, Constella’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 56,728 users and 1,279,126 retweets. Six key communities emerged out of the community detection analysis:

Network topology is characterized by network structures with nodes (profiles) and edges (lines) that connect them. Our algorithms cluster nodes and edges in order to calculate proximities and communities of users.
  1. Murder of Pawel Adamowicz (45.4% of users, 7.9% of retweets): Condolences for the murder of the mayor of Gdansk and expressions of support for the WOSP Foundation. Likewise, many users accuse PiS of being responsible for this event and generating hate language around it.
  2. Affinity to PO (22.5% of users, 41.9% of retweets): Condolences for the murder of Adamowicz, as well as accusations between the different political parties for this incident and incitement of hatred. The resignation of the president of the national public television for subjective manipulation, Jacek Kurski, is also requested.
  3. Affinity to PiS (21.5% of users, 36.4% of retweets): Criticism to PO for taking advantage of the murder of the mayor of Gdansk to engage in politics, as well as for using hate speech and insulting their opponents and the Polish Catholic community
  4. Eurosceptics’ Criticism of PO and PiS (7.7% of users, 12.6% of retweets): Criticisms of PO and PiS for their policies, among them immigration. Requests for responsibility for events in World War 2 concerning Ukrainian and Jewish people. Conversations about the refusal, by referendum, of the Poles to exist outside of the EU
  5. Energy Proposals (1.8% of users, 0.9% of retweets): Debate focused on an energy proposal to reduce dependence on coal. Proposal of a secular school and the separation of Church and State.
  6. Ministry of Foreign Affairs (0.99% of users, 0.3% of retweets): In addition to talking about the death of Mayor Adamowicz, there is talk of Poland’s support (together with the Czech Republic, Estonia, Lithuania, and Latvia) for Ukraine in the face of Russian intervention in Poland.

Politicians Among the Top Communities

In an analysis of influential nodes in the communities mapped, Constella 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 out of 34 politicians in the top communities, 20 (58.82%) were classified in the Affinity to PO community, while 10 (29.4%) were classified within the Affinity to PiS community.

Abnormality detection – Most Active Users

To determine if users demonstrating abnormal levels of activity were present in the debate, Constella’s team focused on an analysis of outliers and their frequency of posting. The results indicated that of the 802 most active users, their average number of comments is 550 with a standard deviation of 378, meaning that users with more than 927 comments are considered outliers. Following this, we identified 89 users (0.16% of all users) demonstrating abnormal activity. This means that over the period of analysis, each abnormal activity user produced at least 39 posts per day resulting in a total of 125,153 (9.76%) total posts.

Users Geolocation

39.70% of users are geolocated in Poland, and 56.09% of users do not publicly express their geolocation. Users posting in Polish from other locations include the United Kingdom (0.69%), the United States (0.61%), and Germany (0.33%).

Role of Traditional, Emerging, and Foreign Media in the Debate

To determine which media sites are most influential, Constella’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. Constella’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.
Constella’s analysis found that traditional Polish 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 include:

– Considerable polarization of the media landscape is characteristic of the communities in the analysis, with the largest communities (Pawel Adamowicz, Affinity to PO, Affinity to PiS) actively engaged on Twitter but sharing very few of the same media domains.

– The Affinity to PO community tended to share sites like wyborcza.pl, onenet.pl, tvn24.pl, wp.pl, and gazeta.pl, among others with high frequency.

– The Affinity to PiS community tended to share domains such as wpolityce.pl, tvp.info, dorzeczy.pl, and niezalezna.pl, among others, with high frequency.

– The Eurosceptics community had a high affinity for sharing domains such as youtube.com, wprawo.pl, nczas.com, and kresy.pl, among others.

Top 150 Domains – Percentage of Times Each Domain Is Shared per Community

Abnormal High Activity Users Analysis

Over a period of analysis from January 21st, 2019 to March 7th, 2019, Constella’s data science team conducted a public digital sphere analysis of high activity users in the Polish sociopolitical conversation. Read the extended analysis here: Polish Public Digital Sphere Debate: Analysis of Abnormal High Activity Users

Interested in our work? Please contact us at info@constellaintelligence.com. To learn more about Constella, subscribe to our newsletter below.

© 2021 Constella Intelligence. All rights reserved. Website Privacy Policy. Terms of Use. Datalake Privacy Notice. Acceptable Use Policy.