Abstract:In recent years we have seen the exponential growth of applications, including dialogue systems, that handle sensitive personal information. This has brought to light the extremely important issue regarding personal data protection in virtual environments. Firstly, a performing model should be able to distinguish sentences with sensitive content from neutral sentences. Secondly, it should be able to identify the type of personal data category contained in them. In this way, a different privacy treatment could be considered for each category. In literature, if there are works on automatic sensitive data identification, these are often conducted on different domains or languages without a common benchmark. To fill this gap, in this work we introduce SPeDaC, a new annotated benchmark for the identification of sensitive personal data categories. Furthermore, we provide an extensive evaluation of our dataset, conducted using different baselines and a classifier based on RoBERTa, a neural architecture that achieves strong performances on the detection of sensitive sentences and on the personal data categories classification.