Privacy-First Situational Awareness Platform for Violent Terrorism and Crime Prediction, Counter Radicalisation and Citizen Protection

Informations projet

CounteR

N° de convention de subvention: 101021607

DOI

10.3030/101021607

Projet clôturé

Date de signature de la CE 26 Avril 2021

Date de début 1 Mai 2021

Date de fin 30 Avril 2024

Financé au titre de

• Secure societies - Protecting freedom and security of Europe and its citizens

Coût total

€ 6 994 812,50

Contribution de l’UE

€ 6 994 812,50

Coordonné par

ASSIST SOFTWARE SRL
Romania

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (14)

Ontology and taxonomy model

Report on ontology and taxonomy model of the solution Related to Task 12

Dissemination Report 12M

Dissemination report for the first year of the project Related to Task 94 and 95

Data protection requirements

Description of the methods to protect data in a secure environment Related to Task 71

Radicalization Ontology, Taxonomy and Recommendations

Report about the basic concepts related to the radicalization process and their relationships Related to Task 24

Psychological factors of the radicalization process

Collection of psychological factors that influence or impact the radicalization process at an individual level Related to Task 22

Review of relevant supranational/ EU/ national laws and regulations

Report on legal requirements of the solution in regards to privacy and personal data protection including all levels of law and regulations supranational EU nationallevel laws of all EU member states Related to Task 13

Social factors of the radicalization process

Collection of social factors that influence or impact the radicalization process at an individual level Related to Task 21

Ethics Briefing Pack 2nd Version

Report on the ethics regulations through all the project tasks final version Related to Task 73

Ethics Briefing Pack 1st Version

Report on the ethics regulations through all the project tasks Intermediary version Related to Task 73

Data management report

Report explaining the data management procedures. Related to Task 10.5.

Dissemination Report 36M

Dissemination report for the 3rd year of the project. Related to Task 9.4 and 9.5

Analysis of radicalization ecosystems on and off-line

Description of the theories to describe the radicalization process related to online and offline factors that impact it Related to task 23

Social Impact Assessment and Recommendations for implementation

Report on the analysis of the Social Impact on potential beneficiaries of the solution and recommendations for the tool implementation. Related to Task 7.4.

Dissemination Report 24M

Dissemination report for the 2nd year of the project Related to Task 94 and 95

Demonstrators, pilots, prototypes (2)

Blogs, forums and Website Data collection

Demo on data collection methods for blogs, forums, and website data. Related to Task 3.2.

Dark and Deep Web collection

Demo on data collection methods for Dark Web data. Related to Task 3.3.

Open Research Data Pilot (1)

Data management plan

Plan for data management including anonymization and data privacy compliance Related to Task 105

Websites, patent fillings, videos etc. (2)

Dissemination materials and templates

Dissemination materials and templates Related to Task 94

Project website

CounteR Project website development and maintenance Related to Task 93

Publications

Conference proceedings (7)

Data-Efficient French Language Modeling with CamemBERTa

Auteurs: Wissam Antoun, Benoît Sagot, Djamé Seddah
Publié dans: Findings of the Association for Computational Linguistics: ACL 2023, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.320

Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language

Auteurs: Arij Riabi, Menel Mahamdi, Djamé Seddah
Publié dans: Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), 2023, Page(s) 266–278
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.law-1.26

Fine-tuning and Sampling Strategies for Multimodal Role Labeling of Entities under Class Imbalance

Auteurs: Syrielle Montariol, Étienne Simon, Arij Riabi, Djamé Seddah
Publié dans: Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations, Numéro May 2022, 2022
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2022.constraint-1.7

Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models

Auteurs: Syrielle Montariol, Arij Riabi, Djamé Seddah
Publié dans: Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, Numéro November 2022, 2022, Page(s) 347–363
Éditeur: Association for Computational Linguistics

Tâches Auxiliaires Multilingues pour le Transfert de Modèles de Détection de Discours Haineux (Multilingual Auxiliary Tasks for Zero-Shot Cross-Lingual Transfer of Hate Speech Detection)

Auteurs: Arij Riabi, Syrielle Montariol, Djamé Seddah
Publié dans: Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale, Numéro June 2022, 2022, Page(s) 413–423
Éditeur: ATALA

EU H2020 project privacy-first situational awareness platform for violent terrorism and crime prediction, counter radicalisation and citizen protection (CounteR)

Auteurs: Marco Anisetti, Michelangelo Ceci
Publié dans: First Italian Conference on Big Data and Data Science, 2022
Éditeur: ITADATA2022

Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?

Auteurs: Arij Riabi, Benoît Sagot, Djamé Seddah
Publié dans: Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), Numéro November 2021, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.wnut-1.47

Other (13)

HURI: Hybrid user risk identification in social networks

Auteurs: Roberto Corizzo, Gianvito Pio, Emanuele Pio Barracchia, Antonio Pellicani, Nathalie Japkowicz, Michelangelo Ceci
Publié dans: Springer World Wide Web, Numéro Volume 26, 2023, Page(s) 3409–3439
Éditeur: Springer World Wide Web

Model-independent methods for embedding directed networks into Euclidean and hyperbolic spaces

Auteurs: Bianka Kovács, Gergely Palla
Publié dans: Numéro July 2022, 2022
Éditeur: Cornell University
DOI: 10.48550/arxiv.2207.07633

Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?

Auteurs: Wissam Antoun, Virginie Mouilleron, Benoît Sagot, Djamé Seddah
Publié dans: 30e Conférence sur le Traitement Automatique des Langues Naturelles, 2023
Éditeur: HAL open science

From Text to Source: Results in Detecting Large Language Model-Generated Content

Auteurs: Wissam Antoun, Benoît Sagot, Djamé Seddah
Publié dans: 2023
Éditeur: Cornell University
DOI: 10.48550/arxiv.2309.13322

SAIRUS: Spatially-aware identification of risky users in social networks

Auteurs: Antonio Pellicani, Gianvito Pio, Domenico Redavid, Michelangelo Ceci
Publié dans: Elsevier Information Fusion, Volume 92, Numéro April 2023, 2023, Page(s) Pages 435-449
Éditeur: Elsevier
DOI: 10.1016/j.inffus.2022.11.029

Extreme digital content: study of radical conversations by ultra-right groups in France

Auteurs: Séraphin Alava, Nawel Chaouni, Nagem Rasha
Publié dans: 2024
Éditeur: Hal open science

Maximally modular structure of growing hyperbolic networks

Auteurs: Sámuel G. Balogh, Bianka Kovács, Gergely Palla
Publié dans: Numéro June 2022, 2022
Éditeur: Cornell University
DOI: 10.48550/arxiv.2206.08773

Analyzing Zero-Shot transfer Scenarios across Spanish variants for Hate Speech Detection

Auteurs: Galo Castillo-lópez, Arij Riabi, Djamé Seddah
Publié dans: Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), Numéro May, 2023, Page(s) 1-13
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.vardial-1.1

Greedy routing optimisation in hyperbolic networks

Auteurs: Bendegúz Sulyok, Gegely Palla
Publié dans: 2023
Éditeur: Sci Rep 13
DOI: 10.48550/arxiv.2303.11456

A Multi-Perspective Approach for Risky User Identification in Social Networks

Auteurs: Antonio Pellicani, Gianvito Pio, Michelangelo Ceci
Publié dans: 2023
Éditeur: SEBD 2023

Femcels speeches between extreme solitude and radical break with the Alpha world

Auteurs: Alava Séraphin, Nagem Rasha
Publié dans: 2024
Éditeur: HAL open science

Generalised popularity-similarity optimisation model for growing hyperbolic networks beyond two dimensions

Auteurs: Bianka Kovács, Sámuel G. Balogh, Gergely Palla
Publié dans: Scientific Reports volume 12, Numéro January 2022, 2022
Éditeur: Scientific Reports volume 12
DOI: 10.1038/s41598-021-04379-1

Subdiffusive semantic evolution in Indo-European languages

Auteurs: Bogdán Asztalos, Gergely Palla, Dániel Czégel
Publié dans: Numéro September 2022, 2022
Éditeur: Cornell University
DOI: 10.48550/arxiv.2209.04701

Peer reviewed articles (1)

 TRA-I and radicalisation processes: current considerations and future perspectives

Auteurs: Barbara Lucini
Publié dans: Report on Terrorism and Radicalization in Europe - N. 3, Year 3, 2022, Page(s) 66-67, ISSN 2813-1045
Éditeur: "#ReaCT2022"