Project: «Preventing Hate Against Refugees and Migrants (PHARM)

Migration to Europe has grown in the last years in scale and complexity. The so called ‘refugee crisis’ and the migratory pressure is particularly acute in southern EU countries as the main entrance to the EU. The main goal of Preventing Hate Against Refugees and Migrants (PHARM) is to monitor and model hate speech against refugees and migrants in Greece, Italy and Spain in order to predict and combat hate crime and also counter its effects using cutting-edge techniques, such as data journalism and narrative persuasion.


The activities distributed in 5 coordinated work packages include:

(i) Implementation of a conceptual and methodological common framework for large-scale analysis and detection of hate speech;

(ii) Implementation and evaluation of machine learning approaches to model and predict hate crimes against refugees and migrants based on hate speech features;

(iii) Survey journalists to understand how they inform and raise awareness about hate speech and how they can help building and disseminating counter-narratives based in data-driven news pieces;

(iv) Creation, evaluation and dissemination of counter-narrative fictional stories adapted to different characteristics of citizens using large-scale narrative persuasion.

PHARM will benefit 500.000 individuals in refugee-like situation, 1.300 journalists, 750 citizens, 7 journalist associations, generic migrants, future asylum seekers and the broad general public who will indirectly benefit from countering strategies. The main result will be the identification and reduction of online hate speech, and the prediction of potential hate crimes.

Anuncio publicitario

Deja una respuesta

Introduce tus datos o haz clic en un icono para iniciar sesión:

Logo de

Estás comentando usando tu cuenta de Salir /  Cambiar )

Imagen de Twitter

Estás comentando usando tu cuenta de Twitter. Salir /  Cambiar )

Foto de Facebook

Estás comentando usando tu cuenta de Facebook. Salir /  Cambiar )

Conectando a %s