Gregoire Burel's profile document
Description for Gregoire Burel
Gregoire Burel
Gregoire Burel
Gregoire
Burel
Research Fellow
I am a research associate and data scientist at the Knowledge Media Institute (KMi) with over 10 years of experience applying Machine Learning (ML) and Natural Language Processing (NLP) techniques in domains such as misinformation detection, crisis event extraction and question answering.
I am currently investigating the spread of misinformation and fact-checks for the Co-Inform (coinform.eu) and HERoS (heros-project.eu) projects. I develop and maintain the Fact-checking Observatory (fcobservatory.org).
Over the years, my work has involved the development and application of machine learning techniques for the investigation of user behaviour in different settings (e.g. answering behaviour, energy consumption habits and emerging behaviour in emergency crises), the development of visualisation tools and platforms (e.g. energyuse.eu, Sparks Prism) and the creation of formal ontological models (e.g. DoRES, EUse,Veracity, Curio).
1b165965382913053cc794fa04168e848841ea48
The Open University account for Gregoire Burel
gb7776
Gregoire Burel's membership at KMi
Gregoire Burel on LinkedIn
@evhart (Gregoire Burel on Twitter)
Gregoire Burel's participation in ROBUST
ROBUST
ROBUST
2010-11-01
2013-10-31
ROBUST aims to analyze, manage and care for online communities to support their well being & to measure their created value.
Online communities have emerged in all areas of society, and their use is now widespread in social, business, scientific and public service domains. They enable the community members to collaborate through shared ideas, knowledge and opinion. Thus, online communities generate major economic value to business and can form pivotal parts of corporate expertise management, corporate marketing, product support, customer relationship management, product innovation and targeted advertising.
The objective of ROBUST is to analyze, manage and care for online communities, in order support their well being, to provide access to the created values and to exploit the knowledge and information contained within. This requires the development of metrics, models and algorithms in several fields.
ROBUST is a 3 year, �6.8M EU project with a consortium of 10 partners from 6 countries. ROBUST is led by the University of Koblenz-Landau, and involves the companies of IBM, SAP, Polecat, Temis, and SoftwareMind, as well as the academic institutions of OU KMi, University of Southampton, National University of Ireland, and the Technical University of Berlin.
Gregoire Burel's participation in COMRADES
COMRADES
COMRADES
2016-01-01
2018-12-31
Collective Platform for Community Resilience & Social Innovation During Crises
Gregoire Burel's participation in HERoS
HERoS
HERoS
Health Emergency Response in Interconnected Systems
HERoS aims to improve the effectiveness and efficiency of the response to the Covid-19 outbreak. HERoS creates and provides policies and guidelines for improved crisis governance, focusing on responders to public health emergencies, and their needs to make informed decisions. HERoS further improves the predictions of the spread by understanding and modelling the impact of local behaviour on the spread of the disease. The OU's role in HERoS is to study the spread of misinformation and corresponding fact-checks related to COVID-19 on social media.
Gregoire Burel's participation in Co-Inform
Co-Inform
Co-Inform
2018-04-01
2021-03-31
Co-Creating Misinformation-Resilient Societies
Misinformation generates misperceptions, which have affected policies in many domains, including economy, health, environment, and foreign policy. Co-Inform is about empowering citizens, journalists, and policymakers with co-created socio-technical solutions, to increase resilience to misinformation, and to generate more informed behaviours and policies. The aim of Co-Inform is to co-create these solutions, with citizens, journalists, and policymakers, for (a) detecting and combating a variety of misinforming posts and articles on social media, (b) supporting, persuading, and nourishing misinformation-resilient behaviour, (c) bridging between the public on social media, external fact checking journalists, and policymakers, (d) understanding and predicting which misinforming news and content are likely to spread across which parts of the network and demographic sectors, (e) infiltrating echo-chambers on social media, to expose confirmation-biased networks to different perceptions and corrective information, and (f) providing policymakers with advanced misinformation analysis to support their policy making process and validation. To achieve these goals, Co-Inform will bring together a multidisciplinary team of scientists and practitioners, to foster co-creational methodologies and practices for engaging stakeholders in combating misinformation posts and news articles, combined with advanced intelligent methods for misinformation detection, misinformation flow prediction, and real-time processing and measurement of crowds' acceptance or refusal of misinformation. Co-Inform tools and platform will be made freely available and open sourced to maximise benefit and reuse. Three main stakeholder groups will be directly engaged throughout this process; citizens, journalists, and policymakers.