In this paper, we sought to model and characterize hate speech against immigrants on Twitter in Spain around the appearance of the far-right party Vox. More than 240,000 tweets that included the term ‘Vox’ between November 2018 and April 2019 were automatically collected and analyzed. Only 1% of the sample included hate speech expressions. Within this subsample of 1977 messages, we found offenses (56%), incitements to hate (42%), and violent speech (2%). The most frequent terms used were classified into five categories: Spain, Immigration, Government, Islam, and Insults. The most common features were foul language, false or doubtful information, irony, distasteful expressions, humiliation or contempt, physical or psychological threats, and incitement to violence. Using unsupervised topic modeling, we found that the four underlying topics (control of illegal immigration, economic assistance for immigrants, consequences of illegal immigration, and Spain as an arrival point for African immigrants and Islamist terrorism) were similar to those in the discourse of Vox. We conclude that the hate speech against immigrants produced around Vox, and not necessarily by Vox, followed the general patterns of this type of speech detected in previous works, including Islamophobia, offensive language more often than violent language, and the refusal to offer public assistance to these collectives.

Hate speech against vulnerable groups is acknowledged as a serious problem for integration and respect for the social diversity existing within the territory of the European Union. The growth of this type of discourse has been supported by the expansion of social media, which have been proven to act as a mechanism for the propagation of crimes against targets such as migrants and refugees, one of the main affected groups. That is why we have conducted the first European study of the social acceptance of migrants and refugees by studying the presence of hate speech. The research is based on the perspective of the theories of intergroup contact and mediated intergroup contact. The methodology includes large-scale longitudinal analysis (2015-2020) of online hate speech on Twitter (N=847,978) and its contrast with existing official indicators. The results suggest that personal intergroup contact is positively corretaled with the support of the local population towards migrants and refugees but mediated intergroup contact is not correlated with hate speech on Twitter. We found evidence that those regions where the support for foreigners was higher, there was a lower level of hate speech on Twitter. This is an advance in the study of hate speech by territories and can help in the formulation of action strategies.El discurso de odio contra públicos vulnerables es reconocido como un grave problema para la integración y el respeto a la diversidad social dentro de la Unión Europea. El aumento de este tipo de discurso se ha visto reforzado con la expansión de las redes sociales, donde se ha demostrado que actúan como mecanismo de propagación de delitos contra colectivos como los migrantes y refugiados, uno de los principales afectados. Por ello se aborda el desarrollo del primer estudio europeo de la aceptación social de migrantes y refugiados mediante el estudio de la presencia de discurso de odio. La investigación se basa en la perspectiva de la teoría del contacto intergrupal y el contacto intergrupal mediado. La metodología incluye el análisis longitudinal (2015-2020) a gran escala del discurso de odio en línea en Twitter (N=847.978) y el contraste con indicadores oficiales existentes. Los resultados apuntan a que el contacto intergrupal personal está correlacionado positivamente con el apoyo de la población hacia migrantes y refugiados, pero el contacto intergrupal mediado no está correlacionado con la disminución del discurso de odio. Encontramos evidencia que muestra que en aquellas regiones en las que el apoyo al colectivo era mayor existía un menor nivel de discurso de odio en Twitter. Esto supone un avance en el estudio del discurso de odio por territorios y puede ayudar en el planteamiento de estrategias de actuación.

Social media messages often provide insights into offline behaviors. Although hate speech proliferates rapidly across social media platforms, it is rarely recognized as a cybercrime, even when it may be linked to offline hate crimes that typically involve physical violence. This paper aims to anticipate violent acts by analyzing online hate speech (hatred, toxicity, and sentiment) and comparing it to offline hate crime. The dataset for this preregistered study included social media posts from X (previously called Twitter) and Facebook and internal police records of hate crimes reported in Spain between 2016 and 2018. After conducting preliminary data analysis to check the moderate temporal correlation, we used time series analysis to develop computational models (VAR, GLMNet, and XGBTree) to predict four time periods of these rare events on a daily and weekly basis. Forty-eight models were run to forecast two types of offline hate crimes, those against migrants and those against the LGBT community. The best model for migrant crime achieved an R2 of 64%, while that for LGBT crime reached 53%. According to the best ML models, the weekly aggregations outperformed the daily aggregations, the national models outperformed those geolocated in Madrid, and those about migration were more effective than those about LGBT people. Moreover, toxic language outperformed hatred and sentiment analysis, Facebook posts were better predictors than tweets, and in most cases, speech temporally preceded crime. Although we do not make any claims about causation, we conclude that online inflammatory language could be a leading indicator for detecting potential hate crimes acts and that these models can have practical applications for preventing these crimes.

Revista sobre bibliotecas, archivos y centros de documentación