Virtual assistants or Intelligent Personal Assistants (IPAs), as they are frequently called in literature, are currently mostly used for simple commands such as setting alarms, playing music, creating reminders, and getting weather information. Contrastingly, the IPAs of the future are envisioned to be personalised, proactive, and capable of performing elaborate tasks. Such systems would have to be based on complex and dynamic user and context models. Scrutability — i.e. the ability of the user to actively study and modify the models towards tuning personalisation — could emerge as an essential element of such a human-assistant interaction paradigm. A closer investigation of personalisation, proactivity, knowledge representation and inference, and scrutability within the context of IPAs is the research challenge of this project.
This research project will examine how the vision of Scrutability in Personalisation may be applied to Proactive IPAs and will be aligned with research from a team in the ADAPT Centre that is examining several challenges related to Proactive Intelligent Personal Assistants.