Conflicting narratives and polarization on social media

• URL: http://arxiv.org/abs/2507.15600v1
• Date: Mon, 21 Jul 2025 13:22:57 GMT
• Title: Conflicting narratives and polarization on social media
• Authors: Armin Pournaki,
• Abstract summary: We show how the analysis of conflicting narratives provides insight into the discursive mechanisms of polarization and issue alignment in the public sphere.<n>Building upon previous work that has identified ideologically polarized issues in the German Twittersphere between 2021 and 2023, we analyze the discursive dimension of polarization.<n>We show evidence for conflicting narratives along two dimensions: (i) different attributions of actantial roles to the same set of actants, and (ii) emplotment of different actants for the same event.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Narratives are key interpretative devices by which humans make sense of political reality. In this work, we show how the analysis of conflicting narratives, i.e. conflicting interpretive lenses through which political reality is experienced and told, provides insight into the discursive mechanisms of polarization and issue alignment in the public sphere. Building upon previous work that has identified ideologically polarized issues in the German Twittersphere between 2021 and 2023, we analyze the discursive dimension of polarization by extracting textual signals of conflicting narratives from tweets of opposing opinion groups. Focusing on a selection of salient issues and events (the war in Ukraine, Covid, climate change), we show evidence for conflicting narratives along two dimensions: (i) different attributions of actantial roles to the same set of actants (e.g. diverging interpretations of the role of NATO in the war in Ukraine), and (ii) emplotment of different actants for the same event (e.g. Bill Gates in the right-leaning Covid narrative). Furthermore, we provide first evidence for patterns of narrative alignment, a discursive strategy that political actors employ to align opinions across issues. These findings demonstrate the use of narratives as an analytical lens into the discursive mechanisms of polarization.

Related papers

• Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models [52.00270888041742]
  We introduce a novel dataset with neutral event descriptions and contrasting viewpoints from different countries.<n>Our findings show significant geopolitical biases, with models favoring specific national narratives.<n>Simple debiasing prompts had a limited effect on reducing these biases.
  arXiv  Detail & Related papers  (2025-06-07T10:45:17Z)
• Talking Point based Ideological Discourse Analysis in News Events [62.18747509565779]
  We propose a framework motivated by the theory of ideological discourse analysis to analyze news articles related to real-world events.<n>Our framework represents the news articles using a relational structure - talking points, which captures the interaction between entities, their roles, and media frames along with a topic of discussion.<n>We evaluate our framework's ability to generate these perspectives through automated tasks - ideology and partisan classification tasks, supplemented by human validation.
  arXiv  Detail & Related papers  (2025-04-10T02:52:34Z)
• Who Sets the Agenda on Social Media? Ideology and Polarization in Online Debates [34.82692226532414]
  This study analyzes large-scale Twitter data from three global debates -- Climate Change, COVID-19, and the Russo-Ukrainian War.<n>Our findings reveal that discussions are not primarily shaped by specific categories of actors, such as media or activists, but by shared ideological alignment.
  arXiv  Detail & Related papers  (2024-12-06T16:48:22Z)
• A graph-based approach to extracting narrative signals from public discourse [4.14360329494344]
  We propose a graph-based formalism and machine-guided method for extracting, representing, and analyzing selected narrative signals. We study political narratives that figure in texts from digital media such as archived political speeches, social media posts, political manifestos and transcripts of parliamentary debates.
  arXiv  Detail & Related papers  (2024-11-01T16:05:59Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse [42.0918839418817]
  We propose a novel topic-agnostic annotation scheme that distinguishes between conspiracies and critical texts. We also contribute with the multilingual XAI-DisInfodemics corpus (English and Spanish), which contains a high-quality annotation of Telegram messages.
  arXiv  Detail & Related papers  (2024-07-15T14:18:47Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Understanding Divergent Framing of the Supreme Court Controversies: Social Media vs. News Outlets [56.67097829383139]
  We focus on the nuanced distinctions in framing of social media and traditional media outlets concerning a series of U.S. Supreme Court rulings. We observe significant polarization in the news media's treatment of affirmative action and abortion rights, whereas the topic of student loans tends to exhibit a greater degree of consensus.
  arXiv  Detail & Related papers  (2023-09-18T06:40:21Z)
• The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning [50.24983453990065]
  We use a deep-learning approach to process a sample of 220 YouTube videos of political leaders from 15 different countries.<n>We observe statistically significant differences in the average score of negative emotions between groups of leaders with varying degrees of populist rhetoric.
  arXiv  Detail & Related papers  (2023-04-19T18:32:49Z)
• Bias or Diversity? Unraveling Fine-Grained Thematic Discrepancy in U.S. News Headlines [63.52264764099532]
  We use a large dataset of 1.8 million news headlines from major U.S. media outlets spanning from 2014 to 2022. We quantify the fine-grained thematic discrepancy related to four prominent topics - domestic politics, economic issues, social issues, and foreign affairs. Our findings indicate that on domestic politics and social issues, the discrepancy can be attributed to a certain degree of media bias.
  arXiv  Detail & Related papers  (2023-03-28T03:31:37Z)
• From Curious Hashtags to Polarized Effect: Profiling Coordinated Actions in Indonesian Twitter Discourse [6.458496335718509]
  Coordinated campaigns in the digital realm have become an increasingly important area of study due to their potential to cause political polarization and threats to security through real-world protests and riots. We introduce a methodology to profile two case studies of coordinated actions in Indonesian Twitter discourse.
  arXiv  Detail & Related papers  (2022-07-16T13:17:30Z)
• Detecting Polarized Topics in COVID-19 News Using Partisanship-aware Contextualized Topic Embeddings [3.9761027576939405]
  Growing polarization of the news media has been blamed for fanning disagreement, controversy and even violence. We propose Partisanship-aware Contextualized Topic Embeddings (PaCTE), a method to automatically detect polarized topics from partisan news sources.
  arXiv  Detail & Related papers  (2021-04-15T23:05:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.