Conversational agents to help people understand politics

Description

In election times, millions of voters consult Voting Advice Applications (VAAs) to learn more about political parties and their standpoints. While VAAs have been shown to enhance political knowledge and increase electoral turnout, research also demonstrates that voters frequently experience comprehension problems when responding to the political attitude statements in a VAA. In the research project I carry out with dr. Naomi Kamoen, we develop and test a new type of VAA, called Conversational Agent VAA (CAVAA), in which users can easily access relevant information about the political issues in the VAA statements by asking questions to a conversational agent. We conducted several experimental studies in which comparisons were made between a) a CAVAA and a regular VAA, b) CAVAA modality, c) several CAVAA designs, d) the CAVAA’s tone of voice. In this presentation I will share the studies’ findings and directions for future research.

Period	1 May 2023
Held at	VU University Amsterdam, department of Artifical Intelligence, Netherlands
Degree of Recognition	Local