Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Decoding the News Media Diet of Disinformation Spreaders

Anna Bertani, Valeria Mazzeo, Riccardo Gallotti

TL;DR

This study employs network science methodologies and entropic measures to analyze the behavioral patterns of social media users sharing news pieces and dig into the diverse news consumption habits within different online social media user groups, finding that those disseminating unreliable content exhibit a more varied and a more regular choice of web-domains.

Abstract

In the digital era, information consumption is predominantly channeled through online news media disseminated on social media platforms. Understanding the complex dynamics of the news media environment and users habits within the digital ecosystem is a challenging task that requires at the same time large bases of data and accurate methodological approaches. This study contributes to this expanding research landscape by employing network science methodologies and entropic measures to analyze the behavioural patterns of social media users sharing news pieces and dig into the diverse news consumption habits within different online social media user groups. Our analyses reveal that users are more inclined to share news classified as fake when they have previously posted conspiracy or junk science content, and vice versa, creating a series of misinformation hot streaks. To better understand these dynamics, we used three different measures of entropy to gain insights into the news media habits of each user, finding that the patterns of news consumption significantly differ among users when focusing on disinformation spreaders, as opposed to accounts sharing reliable or low-risk content. Thanks to these entropic measures, we quantify the variety and the regularity of the news media diet, finding that those disseminating unreliable content exhibit a more varied and at the same time a more regular choice of web domains. This quantitative insight into the nuances of news consumption behaviours exhibited by disinformation spreaders holds the potential to significantly inform the strategic formulation of more robust and adaptive social media moderation policies.

Decoding the News Media Diet of Disinformation Spreaders

TL;DR

This study employs network science methodologies and entropic measures to analyze the behavioral patterns of social media users sharing news pieces and dig into the diverse news consumption habits within different online social media user groups, finding that those disseminating unreliable content exhibit a more varied and a more regular choice of web-domains.

Abstract

In the digital era, information consumption is predominantly channeled through online news media disseminated on social media platforms. Understanding the complex dynamics of the news media environment and users habits within the digital ecosystem is a challenging task that requires at the same time large bases of data and accurate methodological approaches. This study contributes to this expanding research landscape by employing network science methodologies and entropic measures to analyze the behavioural patterns of social media users sharing news pieces and dig into the diverse news consumption habits within different online social media user groups. Our analyses reveal that users are more inclined to share news classified as fake when they have previously posted conspiracy or junk science content, and vice versa, creating a series of misinformation hot streaks. To better understand these dynamics, we used three different measures of entropy to gain insights into the news media habits of each user, finding that the patterns of news consumption significantly differ among users when focusing on disinformation spreaders, as opposed to accounts sharing reliable or low-risk content. Thanks to these entropic measures, we quantify the variety and the regularity of the news media diet, finding that those disseminating unreliable content exhibit a more varied and at the same time a more regular choice of web domains. This quantitative insight into the nuances of news consumption behaviours exhibited by disinformation spreaders holds the potential to significantly inform the strategic formulation of more robust and adaptive social media moderation policies.
Paper Structure (9 sections, 2 equations, 6 figures, 1 table)

This paper contains 9 sections, 2 equations, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Overview of the dataset
  4. News Reliability
  5. Building the information networks
  6. User categories
  7. Entropy
  8. Results
  9. Discussion

Figures (6)

  • Figure 1: The News Media Diet. Network and List of the sequence of web-domains posted by a random user on Twitter. We defined the length of each sequence with the term L. Each sequence is decoded in a list of identified letters. On these lists, we calculate the entropy value to get information about the variety of each sequence. In particular, we performed both random entropy and Shannon entropy calculations for each sequence.
  • Figure 2: Overview of the dataset. (A) Distribution of the length sequence of web-domains respectively for the entire dataset, for users having posted more than 2 distinctive web-domains (N>1), and users defined according the categories of reliability. (B) Distribution of the number messages classified in one of the eight categories of news media types. (C) Distribution of the news media categories used by a user particularly active, which has posted reliable and low-risk content, with 6 distinctive categories of news.
  • Figure 3: The News Media Environment. (A) Weighted networks of the interactions among different news media types (also known as intra-relations) for 25 countries in 2020. (B) Heatmap showing the corresponding value of the inter-relations among the eight categories. (C) Weighted networks normalized comparing with a null model accounting for the proportion of the number of news belonging to each category. The chances of sharing conspiracy and fake news by the same users is much higher than the strong relation observed between mainstream media and political news (Panel A). (D) Heatmap showing the corresponding normalized value of the inter-relations among the eight categories.
  • Figure 4: Self-loops of web-domains and type of news shared. (A) The percentage distribution of the number of self-loops for different users, pointing to the same web-domains, respectively for all the categories considered. (B) The percentage distribution of the number of self-loops of different users, pointing to the same category of news, regardless the different web-domains shared.
  • Figure 5: News Media Diet for different type of users. (A) Random Entropy $S_{rand}$ calculated for different type of accounts: users posting reliable or low-risk content and users posting different levels of high risk (conspiracy/junk science and/or fake/hoax) content. (B) Shannon Entropy $S_{unc}$ calculated on the domain and the type of news shared by different type of users accounts: users posting reliable or low-risk content and users posting different levels of high risk (conspiracy/junk science and/or fake/hoax) content. (C) The actual entropy $S$ calculated on the domain and news media categories shared by different type of users: those posting reliable or low-risk content and those posting different levels of high risk (conspiracy/junk science and/or fake/hoax) content.
  • ...and 1 more figures