230025 Evaluation and Expectations of Conversational Agents (S) (WiSe 2026/2027)

In this seminar we will look at methods that are used for the evaluation of interactions with conversational agents (e.g. voice assistants like Alexa, or robots). In order to see in which areas different evaluations are carried out, we look at current research (papers, studies) that deal with the expectations of users regarding these artificial agents, and perceptions of the interactions with them.
In human-machine interaction, the expectations of users are relevant for various reasons, for example to improve communication between humans and machines and subsequently to better evaluate their interaction.
We will therefore begin by discussing methods for querying expectations of human-machine interaction for various agents. We will then look at methods for evaluating interaction with conversational agents. This seminar will be held in English.

Literaturangaben

As supporting/basis literature we will use the following books:
- Bartneck, C., Belpaeme, T., Eyssel, F., Kanda, T., Keijsers, M., & Sabanovic, S. (2020). Human-Robot Interaction – An Introduction. Cambridge: Cambridge University Press. www.human-robot-interaction.org (especially Chapter 9 "Research Methods")
- Jost et al. (2020) Human-Robot Interaction: Evaluation Methods and their Standardization. https://doi.org/10.1007/978-3-030-42307-0