Learn, Explore and Reflect by Chatting: Understanding the Value of an LLM-Based Voting Advice Application Chatbot

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Jianlong, Kempermann, Manon, Cannanure, Vikram Kamath, Hartland, Alexander, Navarrete, Rosa M., Carteny, Giuseppe, Braun, Daniela, Weber, Ingmar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913838469742592
author Zhu, Jianlong
Kempermann, Manon
Cannanure, Vikram Kamath
Hartland, Alexander
Navarrete, Rosa M.
Carteny, Giuseppe
Braun, Daniela
Weber, Ingmar
author_facet Zhu, Jianlong
Kempermann, Manon
Cannanure, Vikram Kamath
Hartland, Alexander
Navarrete, Rosa M.
Carteny, Giuseppe
Braun, Daniela
Weber, Ingmar
contents Voting advice applications (VAAs), which have become increasingly prominent in European elections, are seen as a successful tool for boosting electorates' political knowledge and engagement. However, VAAs' complex language and rigid presentation constrain their utility to less-sophisticated voters. While previous work enhanced VAAs' click-based interaction with scripted explanations, a conversational chatbot's potential for tailored discussion and deliberate political decision-making remains untapped. Our exploratory mixed-method study investigates how LLM-based chatbots can support voting preparation. We deployed a VAA chatbot to 331 users before Germany's 2024 European Parliament election, gathering insights from surveys, conversation logs, and 10 follow-up interviews. Participants found the VAA chatbot intuitive and informative, citing its simple language and flexible interaction. We further uncovered VAA chatbots' role as a catalyst for reflection and rationalization. Expanding on participants' desire for transparency, we provide design recommendations for building interactive and trustworthy VAA chatbots.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09806
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learn, Explore and Reflect by Chatting: Understanding the Value of an LLM-Based Voting Advice Application Chatbot
Zhu, Jianlong
Kempermann, Manon
Cannanure, Vikram Kamath
Hartland, Alexander
Navarrete, Rosa M.
Carteny, Giuseppe
Braun, Daniela
Weber, Ingmar
Human-Computer Interaction
Computers and Society
Voting advice applications (VAAs), which have become increasingly prominent in European elections, are seen as a successful tool for boosting electorates' political knowledge and engagement. However, VAAs' complex language and rigid presentation constrain their utility to less-sophisticated voters. While previous work enhanced VAAs' click-based interaction with scripted explanations, a conversational chatbot's potential for tailored discussion and deliberate political decision-making remains untapped. Our exploratory mixed-method study investigates how LLM-based chatbots can support voting preparation. We deployed a VAA chatbot to 331 users before Germany's 2024 European Parliament election, gathering insights from surveys, conversation logs, and 10 follow-up interviews. Participants found the VAA chatbot intuitive and informative, citing its simple language and flexible interaction. We further uncovered VAA chatbots' role as a catalyst for reflection and rationalization. Expanding on participants' desire for transparency, we provide design recommendations for building interactive and trustworthy VAA chatbots.
title Learn, Explore and Reflect by Chatting: Understanding the Value of an LLM-Based Voting Advice Application Chatbot
topic Human-Computer Interaction
Computers and Society
url https://arxiv.org/abs/2505.09806