Pan-European Observatory for Mitigation of Hate Speech (PANORAMA)

Countering online hate speech has proven increasingly challenging due to the ever-shifting dynamics of our online environment. If we want to counter online hate speech successfully, we need to conduct ground-breaking big data research on the fundamental nature of these dynamics. We need to address issues of language, networks, influence media.

Objective

The new European Observatory of Online Hate (EOOH) will bring together all stakeholders along with transparent AI for all European languages. The aim is to get a grip on evolving online hate speech trends, after which experts can use the collected insights for early or reconciliatory countermeasures. 

Over the course of the initiative’s R&D cycle, new ‘Explainable AI’ will be developed to analyse online trends in all European language regions, which human experts can then use for information gathering and advocacy campaigns with positive counter narratives. The project consortium coordinated by Textgain, and partners Hogeschool Utrecht, Dare to be Grey, and PDCS ( dtbg.nl , hu.nl , pdcs.sk ) will reach out to and promote dialogue between more than 50 partner organizations, including European law enforcement and security agencies, policy makers, human rights organizations, and investigative journalism and citizen science initiatives.

Results

  • Increased knowledge on the phenomenon of hate speech online and the dynamics of it's profile.
  • Strengthened cooperation between public authorities, civil society organisations and internet companies, in particular in the areas of prevention, reporting, education and awareness-raising about tolerance and inclusion;
  • Increased awareness of the general public, particularly young people, on online hate speech, through the promotion of positive narratives and online campaigns

Preliminary results
Several blogs have been published around the project:

 

"We are interested in the increasingly outspoken toxic language being used on social media that drives real-life conflict and harm, how people express discontent and why"

Gijs van Beek
projectmanager Texgain

Duration

01 January 2021 - 01 July 2023

Approach

This project involves the following steps:

  • Toxicity lexicons in 24 EU languages integrated into a European-wide ontology of hate speech.
  • Development of Explainable AI (XAI) processing technologies to interface with the ontology.
  • User experience (UX) design for the various user groups of the Pan-European Observatory for Mitigation of Hate Speech.
  • Series of round-table events in Belgium and Slovakia with experts discuss topics arising from the collected data and dashboard analysis.
  • These national-level events will be complemented by three pan-European roundtables focusing on issues relating to the project’s EU dimension.
  • Outputs from the expert roundtables will be published disseminated in reports and transformed into social media content.
  • This content will include positive alternative narratives as well as “rapid response” items that address urgent focus areas.
  • They will be disseminated through a youth-focused awareness-raising campaign
  • The project will end with a closing conference which will bring together a wider pool of experts and a pan-European audience.

HU researchers involved in the research

  • Anand Sheobar
    Anand Sheombar
    • Researcher
    • Research group: Process Innovation and Information Systems
  • Pascal Ravesteijn | Professor | Process innovation and information systems
    Pascal Ravesteijn
    • Professor
    • Research group: Process Innovation and Information Systems

Collaboration with knowledge partners

The project consortium is coordinated by Textgain, and the other partners involved are Hogeschool Utrecht, Dare to be Grey, and PDCS ( dtbg.nl , hu.nl , pdcs.sk). This research is (partially) funded by the EU, project  ID 963801 under call REC-AG-2020.

Any questions or want to collaborate?

Anand Sheobar

Anand Sheombar

  • Researcher
  • Research group: Process Innovation and Information Systems