A data science approach to social science problems: examining political bias in false information on social media

June 12th, 2020 by

The 2016 United States (U.S) presidential election highlighted the powerful influence that social media can have on politics. Fake news stories shared on social media are argued to have swayed the outcome of the last U.S. election and a recent article in the Guardian questioned: “Will fake news wreck the coming [UK] general election?”

With the Conservatives recently spending approximately £100,000 and the Brexit party spending £107,000 on Facebook advertising in the UK, it is becoming increasingly important to understand how false information on social media is politically biased.

As part of their role in the EU funded EUNOMIA (user-oriented, secure, trustful & decentralised social media) project, Trilateral’s research team sought to address this question.

EUNOMIA is a three-year (2018-2021) project that brings together 10 partners who will develop a decentralised, open-source solution to assist social media users (traditional media journalists, social journalists and citizen users) in determining the trustworthiness of information.

An interdisciplinary approach

Trilateral leads the work in EUNOMIA to understand the social and political considerations in the verification of social media information. The research team’s interdisciplinary approach drew on the expertise of social scientists from the Applied Research & Innovation team and data scientists from the technical team.

The social science research comprised of desk-based research and 19 semi-structured interviews with citizen social media users, traditional media journalists, social journalists and other relevant stakeholders.

Participant observation has been undertaken through a data science approach designed to examine political bias in relation to the engagement with false information. To do this the study focused on the political leanings of false information accounts in relation to UK political parties. The data science methodology included:

  • Web scraping to identify the Twitter handles of the 579 UK MPs and 49 false information organisations which included organisations labelled as “conspiracy-pseudoscience” or “questionable” sources on the Mediabiasfactcheck.com database and climate change denial organisations listed on the DeSmog Climate Disinformation Research Database
  • Data mining on Twitter, processing and utilising big data exclusively using the publicly available Twitter APIs
  • Social network analysis to track the following between the examined accounts and extract insights to measure political bias
EUNOMIA fake news

To examine political bias in relation to false information, the technical team analysed three metrics, including:

  1. The intersection of the followers of each false information account and the followers of the Conservative and Labour MPs
  2. A social network graph highlighting the political bias of the followers of each false information account
  3. Whether false information accounts follow more Conservative or Labour MPs

The findings of all three metrics examined indicate that the majority of false information accounts in this study are Conservative-leaning.

Whilst these findings may be the result of the calls by Conservative-leaning politicians to distrust mainstream media or in how accounts are labelled as false information by fact-checkers, the presence of political bias in social media content can result in it being distrusted.

The interview findings highlighted how information and sources that are politically biased or radicalised are not perceived to be trustworthy. As interviewees highlighted how the language used can provide insights into political bias, our further research will draw on natural language processing techniques to explore the language used when engaging with false information accounts.

The findings of this study have been submitted for publication as a journal article.

Disclaimer: This post first published on Trilateral Research website

Addressing fake news and disinformation on social media

March 31st, 2020 by

Fake news have the power to build a misleading representation of reality posing a threat to our security and safety and forcing us to consider how we can build trust in information.

The ability for users to generate, share and engage with social media content means that there is a vast amount of information on social media. While users regularly access social media for the latest news and information, this information cannot always be trusted.

For example, the 2011 riots in the UK saw the use of social media for disinformation, the deliberate spread of false rumours about topics such as looting. It was during the 2016 US elections that the concept of “fake news” became mainstream, referring to unverified news stories and deliberate disinformation. This issue is only likely to increase with the emergence of “deep fake videos” that can be easily created by combining different videos and images and then shared on social media, examples include the use of machine learning techniques to develop lip-syncing videos of Barack Obama giving a speech by George W. Bush. Beyond research, in some more serious cases, the spread of disinformation can have the potential for life and death consequences when inaccurate information is spread in relation to issues such as disaster response or healthcare.

For example, when Hurricane Sandy swept across parts of the USA and the Caribbean, numerous people and organisations took to the web to search for and share information. As is commonly the case, some of this information was grossly untrue. Fake news was not limited to written content but images too, including sharks in flood waters and lady Liberty under attack from killer waves.

EUNOMIA project addresses these challenges associated with fake news and disinformation.

What is the EUNOMIA project?

EUNOMIA (user-oriented, secure, trustful & decentralised social media) is a European Union funded project that will assist users in determining the trustworthiness of social media information using an intermediary-free open-source approach. EUNOMIA will address the following questions focusing predominantly on decentralised social media:

– Which social media user is the original source of a piece of information?

– How has this information spread and been modified in an information cascade?

– How likely is the information to be trustworthy?

The 10 consortium partners will provide social media users with a technical platform and software tools that will enable them to vote on the trustworthiness of each social media post. Thus, EUNOMIA addresses the challenge of disinformation in social media by enabling users themselves to take ownership of their engagement with social media.

Identifying fake news on social media

What role does Trilateral play in EUNOMIA?

Trilateral adopts a cross-cutting and interdisciplinary approach to their work in the EUNOMIA project focusing on:

  • Primary applied social science research: Trilateral leads EUNOMIA’s work on human and societal factors. We will draw on our expertise in co-design and primary research (i.e., interviews, workshops) to engage with stakeholders to understand the social and political factors involved in the verification of information on social media
  • Technology and data science: Building on our applied social science research, our interdisciplinary team will apply network analysis, natural language processing, and machine learning to gain insights from data extracted via social media APIs (e.g., Twitter, Mastodon) on the social (e.g., age, gender, nationality) and political factors involved in the verification of information
  • Privacy Impact Assessment+: Trilateral is working in partnership with the technical developers and end-users to conduct a privacy, social and ethical impact assessment (PIA+) of the EUNOMIA tools to ensure that the project takes a privacy and data protection-by-design approach
  • Co-design and Stakeholder engagement: Trilateral leads the ongoing liaison and engagement with relevant stakeholders that will benefit from the outputs of the EUNOMIA solution ensuring co-design approaches are integrated across the project

Trilateral will undertake this work in collaboration with the other partners, including the University of Greenwich, SIVECO, Blasting News, Inov Insec Inovação, University of West Attica, University of Nicosia, Österreichischer Rundfunk (ORF), Eugen Rochko (Mastodon Social), and SYNYO GmbH. Representatives from all partners were brought together for the EUNOMIA kick-off meeting that took place in Greenwich (UK) in January 2019. The kick-off meeting provided the perfect opportunity for the partners to plan the work for the next three years.

EUNOMIA consortium at kick off meeting

Partners at the EUNOMIA kick-off meeting, Greenwich (UK)

Disclaimer: This post first published on Trilateral Research website