Contributed talk at ECML/PKDD in Vilnius, Lithuania.

I presented my paper on adaptive questionnaires (Bachmann et al., 2024) in the multitask meta-learning session and also had a poster presentation. Additionally, I participated in the Ph.D. forum with a 20-minute talk.

Highlights included keynotes from DeepMind and Moritz Hardt. A very well-organized conference with great social activities — and Vilnius turned out to be an unexpectedly amazing city!

The eﬀectiveness of Voting Advice Applications is often compromised by the length of their questionnaires. To address user fatigue and incomplete responses, some applications (such as the Swiss Smartvote) oﬀer a condensed version of their questionnaire. However, these condensed versions cannot ensure the accuracy of recommended parties or candidates, which we show to remain below 40%. To address these limitations, this work introduces an adaptive questionnaire approach that selects subsequent questions based on users’ previous answers, aiming to enhance recommendation accuracy while reducing the number of questions posed to the voters. Our method uses an encoder and decoder module to predict missing values at any completion stage, leveraging a two-dimensional latent space that is reﬂective of the traditional methods used in political science for visualizing ideology. Additionally, a selector module is proposed to determine the most informative subsequent question based on the voter’s current position in the latent space and the remaining unanswered questions. We validated our approach using the Smartvote dataset from the Swiss Federal elections in 2019, testing various spatial models and selection methods to optimize the system’s predictive accuracy. Our ﬁndings indicate that employing the IDEAL model both as encoder and decoder, combined with a PosteriorRMSE method for question selection, signiﬁcantly improves the accuracy of recommendations, achieving 74% accuracy after asking the same number of questions as in the condensed version.