The hate speech on social media They advance without, for the moment, there being effective formulas to stop them. Technological platforms are putting measures to neutralize them, however they are not having the expected results. It is necessary to attack them in another way, with artificial intelligenceas is being done by the SINAI (Intelligent Information Access Systems) research group of the University of Jaén (UJA), through the project ‘MODERATES: Content Moderation on Social Networks’.
In a context of exponential growth of social networks and rapid expansion of digital communication, it is essential ensure a safe and respectful online environment for all users.
How the UJA fights hate speech with artificial intelligence
With the MODERATES project it is proposed to develop artificial intelligence tools and techniques based on Natural Language Processing (NLP), in order to preventatively detect hate speech and offer solutions that promote constructive dialogue.
These techniques, inspired by innovative developments such as those behind the famous ChatGPTallow the SINAI group to go a step further and design tools that allow the mitigation of negative speech through the automatic generation of counter narratives, enriching the digital environment with positive and constructive messages.
The main researchers of the project, the professors of the University of Jaén L. Alfonso Urena and Maria Theresa Martin, underline the importance of this initiative. «The moderation of content on social networks is a current challenge that requires the collaboration of academia, industry and society in general. Our objective is develop automated systems that identify and combat hate speech, thus fostering a safer virtual environment and enriching for all users”, they declare.
What does the MODERATES project represent?
The project, which has funding of almost 300,000 euros corresponding to the call for Ecological and Digital Transition of the Ministry of Science and Innovation, represents a significant advance in the application of language-based artificial intelligence technologies to promote more constructive online communication and thanks to it, the SINAI Group of the University of Jaén, which has extensive experience in the development of systems based on artificial intelligence for the detection of hate speech, takes another step to address this social problem and work on its mitigation.
Both the SINAI Group, which since its foundation in 2001 has been dedicated to the study and research of the PLN, and the University of Jaén itself, are committed to promoting scientific research and innovation. In this way, this new project, in which more than a dozen senior researchers who are PLN experts are working, adds to the efforts to contribute to the advancement of society in the digital era and is expected to have a significant impact both from the start scientific and social point of view in promoting a more respectful and constructive online communication.