Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Knowledge Graph Representation for Political Information Sources

Tinatin Osmonova, Alexey Tikhonov, Ivan P. Yamshchikov

TL;DR

The paper investigates how echo-chambers arise in political information consumption by analyzing long-running news data from Breitbart News and the New York Times using knowledge-graph representations. It builds entity-graphs from NLP extractions (open information extraction and named entity recognition) with sentiment and subjectivity annotations, linking entities by relations weighted by frequency and polarity. Findings indicate both sources are broadly neutral on average, with polarization concentrated on a small set of entities and distinct differences in domestic versus international topics, suggesting that echo-chambers may stem from individual information consumption rather than social network topology. The study provides a data-and-methods contribution by sharing the graphs and demonstrating a knowledge-representation approach for political discourse analysis, with implications for understanding audience worldviews.

Abstract

With the rise of computational social science, many scholars utilize data analysis and natural language processing tools to analyze social media, news articles, and other accessible data sources for examining political and social discourse. Particularly, the study of the emergence of echo-chambers due to the dissemination of specific information has become a topic of interest in mixed methods research areas. In this paper, we analyze data collected from two news portals, Breitbart News (BN) and New York Times (NYT) to prove the hypothesis that the formation of echo-chambers can be partially explained on the level of an individual information consumption rather than a collective topology of individuals' social networks. Our research findings are presented through knowledge graphs, utilizing a dataset spanning 11.5 years gathered from BN and NYT media portals. We demonstrate that the application of knowledge representation techniques to the aforementioned news streams highlights, contrary to common assumptions, shows relative "internal" neutrality of both sources and polarizing attitude towards a small fraction of entities. Additionally, we argue that such characteristics in information sources lead to fundamental disparities in audience worldviews, potentially acting as a catalyst for the formation of echo-chambers.

Knowledge Graph Representation for Political Information Sources

TL;DR

The paper investigates how echo-chambers arise in political information consumption by analyzing long-running news data from Breitbart News and the New York Times using knowledge-graph representations. It builds entity-graphs from NLP extractions (open information extraction and named entity recognition) with sentiment and subjectivity annotations, linking entities by relations weighted by frequency and polarity. Findings indicate both sources are broadly neutral on average, with polarization concentrated on a small set of entities and distinct differences in domestic versus international topics, suggesting that echo-chambers may stem from individual information consumption rather than social network topology. The study provides a data-and-methods contribution by sharing the graphs and demonstrating a knowledge-representation approach for political discourse analysis, with implications for understanding audience worldviews.

Abstract

With the rise of computational social science, many scholars utilize data analysis and natural language processing tools to analyze social media, news articles, and other accessible data sources for examining political and social discourse. Particularly, the study of the emergence of echo-chambers due to the dissemination of specific information has become a topic of interest in mixed methods research areas. In this paper, we analyze data collected from two news portals, Breitbart News (BN) and New York Times (NYT) to prove the hypothesis that the formation of echo-chambers can be partially explained on the level of an individual information consumption rather than a collective topology of individuals' social networks. Our research findings are presented through knowledge graphs, utilizing a dataset spanning 11.5 years gathered from BN and NYT media portals. We demonstrate that the application of knowledge representation techniques to the aforementioned news streams highlights, contrary to common assumptions, shows relative "internal" neutrality of both sources and polarizing attitude towards a small fraction of entities. Additionally, we argue that such characteristics in information sources lead to fundamental disparities in audience worldviews, potentially acting as a catalyst for the formation of echo-chambers.
Paper Structure (8 sections, 8 figures, 1 table)

This paper contains 8 sections, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Data and Methodology
  3. Do You Know What I Know?
  4. Bird's-eye View
  5. Politics of Contrasts
  6. Discussion
  7. Conclusion
  8. Bibliographical References

Figures (8)

  • Figure 1: Breitbart News. Distribution of sentiment.
  • Figure 2: New York Times. Distribution of sentiment.
  • Figure 3: Breitbart News. Distribution of subjectivity.
  • Figure 4: New York Times. Distribution of subjectivity.
  • Figure 5: Breitbart News. Overall visualisation of two graphs extracted out of the media sources. The classes found with modularity analysis blondel2008fast are highlighted with different colours. Breitbard has smaller number of classes and is centered around US political discourse.
  • ...and 3 more figures