:partying_face: Short Paper accepted at ACM CUI Conference! :de:

Our paper on a behavioral typology of user engagement in Conversational Agent Voting Advice Applications (CAVAAs) (Van Der Weijden et al., 2026) has been accepted at the 2026 ACM Conference on Conversational User Interfaces (CUI ‘26) in Bremen, Germany!

Using interaction data from 189 users of a GPT-driven CAVAA during the 2024 European Parliament elections, a Latent Class Analysis reveals three user types — Checkers (low interaction), Seekers (high engagement and uncertainty), and Testers (system probing rather than advice seeking). Furthermore, we find that the chatbot persona predicts completion of the CAVAA: the more active, follow-up question asking chatbot increased dropout rates. This informs design decisions for CAVAA implementations.

Thank you to my co-first authors Daan van der Weijden and Thilo Iganz Dieing for the great collaboration, and to the anonymous reviewers for their helpful feedback!

Looking forward to presenting our work in Bremen this July!

Voting Advice Applications (VAAs) help citizens align with political parties, but are limited by frequent comprehension problems. Conversational Agent VAAs (CAVAAs) address this by integrating chatbot-based support. Yet, user interaction patterns and their effects on completing the CAVAA remain underexplored. This study identifies behavior-based CAVAA user types and examines their interaction with chatbot personas. Using interaction data from 189 users of an GPT-driven CAVAA during the 2024 European Parliament elections, a Latent Class Analysis reveals three types: Checkers (low interaction), Seekers (high engagement and uncertainty), and Testers (system probing rather than advice seeking). While user types do not predict completion, the chatbot personas significantly did. We find that the more active chatbot (asking follow-up questions) increased dropout rates. Our analysis introduces a novel behavioral typology and highlights the importance of conversational design for reducing dropout and improving CAVAA effectiveness.