Technologies to address online bullying are limited to detecting and hiding abusive messages, or provide a single automated reply. Conversational technologies are underused assets for addressing abusers. We will present our initial experiments and our research directions for investigating different dialog strategies (e.g., to educate or deter abusers, or keep them busy with chatbots rather than their victims). We will also discuss fundamental issues with deploying chatbots for behavior manipulation on social media (e.g., failures and unintended consequences).
Senior Track Associate @ Amsterdam University of Applied Science
Microsoft AI MVP