A Web Interface for Analyzing Hate Speech

Vrysis, Lazaros; Vryzas, Nikolaos; Kotsakis, Rigas; Saridou, Theodora; Matsiola, María; Veglis, Andreas; Calderón, Carlos Arcila; Dimoulas, Charalampos

doi:10.3390/fi13030080

Cited by 30 publications

(24 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Online hate speech has been identified as a pressing problem in society, with experts from different fields of investigation looking for approaches to detect and prevent it. Recent research implements and evaluates innovative tools to deal with this phenomenon (Vrysis et al, 2021) and analyses emotional responses and the construction of "alternative counternarratives to this socially alive issue" (Ortega-Sánchez et al, 2021, p. 1).…”

Section: Cda Stage 5 Discussion: Reflections On the Analysis And The ...mentioning

confidence: 99%

Public relations and dissent: Anti-racism digital advocacy Portuguese case study

Müller

2022

Communication & Society

View full text Add to dashboard Cite

Social media platforms are being used to shift the balance of power, functioning as tools of resistance for activist publics on social justice issues. This article uses a postmodern approach to public relations with the purpose of clarifying the role of dissensus in social media contexts, connecting it to the principles of the ethics of care that promote dialogue but not necessarily with the aim of achieving consensus. Scholars and practitioners can claim a broader role for public relations in society by considering and analyzing conflicting perspectives in digital communication as a way to engage with activist struggles in social justice and human rights causes. By applying critical discourse analysis (CDA) to a case study that articulates interdisciplinary concepts, this research analyzes the first national weekly Portuguese newspaper Expresso support for the anti-racist cause through its promotion of a manifesto and a Facebook post against racist intimidation. In a contemporary society characterized by fragmentation, taking a public stance on important social and political issues, as in the case analyzed, demands moving beyond consensus-driven communication. The data confirm that social media platforms are not necessarily dialogic spaces and that conflicting communicative perspectives may be a useful way to analyze social change in public relations theory and practice. By taking a public stand against racist intimidation, assuming the possible alienation of specific publics –and “Facebook bullying”– this private newspaper also demonstrated the practical application of the assumptions of the ethics of care.

show abstract

Section: Cda Stage 5 Discussion: Reflections On the Analysis And The ...mentioning

confidence: 99%

Public relations and dissent: Anti-racism digital advocacy Portuguese case study

Müller

2022

Communication & Society

View full text Add to dashboard Cite

show abstract

“…Other datasets were found that also contained texts in Spanish, but were not exclusively in Spanish, as in the case of the PHARM project, where the dataset is composed of texts in Spanish, Italian and Greek ( Vrysis et al, 2021 ).…”

Section: Related Workmentioning

confidence: 99%

Detecting racism and xenophobia using deep learning models on Twitter data: CNN, LSTM and BERT

Benítez-Andrades

González-Jiménez

López-Brea

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

With the growth that social networks have experienced in recent years, it is entirely impossible to moderate content manually. Thanks to the different existing techniques in natural language processing, it is possible to generate predictive models that automatically classify texts into different categories. However, a weakness has been detected concerning the language used to train such models. This work aimed to develop a predictive model based on BERT, capable of detecting racist and xenophobic messages in tweets written in Spanish. A comparison was made with different Deep Learning models. A total of five predictive models were developed, two based on BERT and three using other deep learning techniques, CNN, LSTM and a model combining CNN + LSTM techniques. After exhaustively analyzing the results obtained by the different models, it was found that the one that got the best metrics was BETO, a BERT-based model trained only with texts written in Spanish. The results of our study show that the BETO model achieves a precision of 85.22% compared to the 82.00% precision of the mBERT model. The rest of the models obtained between 79.34% and 80.48% precision. On this basis, it has been possible to justify the vital importance of developing native transfer learning models for solving Natural Language Processing (NLP) problems in Spanish. Our main contribution is the achievement of promising results in the field of racism and hate speech in Spanish by applying different deep learning techniques.

show abstract

“…Crowdsourcing is a methodology for distributed problem-solving that happens online by the collective intelligence of a community in a specific predefined direction set by an organization [49]. It has gained interest thanks to its efficiency and applicability in multiple domains and tasks [57][58][59][60][61]. In machine learning and automation, it has become very popular for collaborative problem solving and dataset formulation and validation [57,59].…”

Section: Crowdsourcing For Dataset Creation Validation and User Coope...mentioning

confidence: 99%

“…The web application was designed using the Flask web framework. This was a rational choice, taking into consideration the popularity of the Python programming language for data analysis and the successful deployment of similar web applications by our team [61]. The selection of a popular programming environment for such tasks may make the extendibility of the framework by contributors more appealing and viable.…”

Section: Implementation and Deployment Of The Prototype For Human-cen...mentioning

confidence: 99%

A Prototype Web Application to Support Human-Centered Audiovisual Content Authentication and Crowdsourcing

et al. 2022

Self Cite

View full text Add to dashboard Cite

Media authentication relies on the detection of inconsistencies that may indicate malicious editing in audio and video files. Traditionally, authentication processes are performed by forensics professionals using dedicated tools. There is rich research on the automation of this procedure, but the results do not yet guarantee the feasibility of providing automated tools. In the current approach, a computer-supported toolbox is presented, providing online functionality for assisting technically inexperienced users (journalists or the public) to investigate visually the consistency of audio streams. Several algorithms based on previous research have been incorporated on the backend of the proposed system, including a novel CNN model that performs a Signal-to-Reverberation-Ratio (SRR) estimation with a mean square error of 2.9%. The user can access the web application online through a web browser. After providing an audio/video file or a YouTube link, the application returns as output a set of interactive visualizations that can allow the user to investigate the authenticity of the file. The visualizations are generated based on the outcomes of Digital Signal Processing and Machine Learning models. The files are stored in a database, along with their analysis results and annotation. Following a crowdsourcing methodology, users are allowed to contribute by annotating files from the dataset concerning their authenticity. The evaluation version of the web application is publicly available online.

show abstract

A Web Interface for Analyzing Hate Speech

Cited by 30 publications

References 46 publications

Public relations and dissent: Anti-racism digital advocacy Portuguese case study

Public relations and dissent: Anti-racism digital advocacy Portuguese case study

Detecting racism and xenophobia using deep learning models on Twitter data: CNN, LSTM and BERT

A Prototype Web Application to Support Human-Centered Audiovisual Content Authentication and Crowdsourcing

Contact Info

Product

Resources

About