4 papers
Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents
Erika Elizabeth Taday Morocho, Lorenzo Cima, Tiziano Fagni +2
Using persona-conditioned LLMs as synthetic survey respondents has become a common practice in computational social science and agent-based simulations. Yet, it remains unclear whe…
Quantifying Feature Importance for Online Content Moderation
Benedetta Tessa, Alejandro Moreo, Stefano Cresci +2
Accurately estimating how users respond to moderation interventions is paramount for developing effective and user-centred moderation strategies. However, this requires a clear und…
Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets
Tommaso Giorgi, Lorenzo Cima, Tiziano Fagni +2
The rise of online platforms exacerbated the spread of hate speech, demanding scalable and effective detection. However, the accuracy of hate speech detection systems heavily relie…
The DSA Transparency Database: Auditing Self-reported Moderation Actions by Social Media
Amaury Trujillo, Tiziano Fagni, Stefano Cresci
Since September 2023, the Digital Services Act (DSA) obliges large online platforms to submit detailed data on each moderation action they take within the European Union (EU) to th…