Evaluating Trustworthiness and Interpretability of eXplainable AI Techniques for Cyberbullying Detection

  • Home/
  • Evaluating Trustworthiness and Interpretability of eXplainable AI Techniques for Cyberbullying Detection

Evaluating Trustworthiness and Interpretability of eXplainable AI Techniques for Cyberbullying Detection

1st International Workshop on Symbiotic AI for Cyber Social Security (SAI4CSS) - -2026

Authors

Loseto Giuseppe, Gramegna Filippo, Pinto Agnese, Scioscia Floriano, Ruta Michele

DOI

https://doi.org/10.1109/access.2025.3552112

BibTex references

@InProceedings{LGPSR26,
  author       = "Loseto, Giuseppe and Gramegna, Filippo and Pinto, Agnese and Scioscia, Floriano and Ruta, Michele",
  title        = "Evaluating Trustworthiness and Interpretability of eXplainable AI Techniques for Cyberbullying Detection",
  booktitle    = "1st International Workshop on Symbiotic AI for Cyber Social Security (SAI4CSS)",
  year         = "2026",
  note         = "to appear",
  url          = "http://sisinflab.poliba.it/Publications/2026/LGPSR26"

}