Research areaSocial Media
We model ethotic profiles of users on social media in order to enhance technologies of Explainable Artificial Intelligence. We define, design, develop and validate a new methodology for argumentation schemes tailored for planning and handling the discourse history in interactive conversational agents aimed at explaining AI in NL. The customization is achieved through the creation of a profile of the user and then adaptation of argumentation to match this profile. This involves both the analysis and the representation of the use of argumentation in natural communication in the specific genre, and the application of previous pioneering work on ethotic strategies in NL, i.e., on the communicative behaviour dependent on the character of the speaker.
The work will allow us to gain understanding of the state of the art in relevant aspects of argumentation theory and dialogue systems for XAI; to collect analysis SWOT of existing argumentation schemes and their extensions (including ethotic extensions) for conversational agents; to develop definition and implementation of a new protocol for handling profiles of users and the discourse history with explanation purposes; and to execute validation of this protocol in two use cases.
This work is supported by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860621.
To find out more, go to:
TO BE ANNOUNCED SOON