Voting advice applications (VAA) allow potential voters to compare their own policy positions to political parties running for an election. One of the key design elements of a VAA are the policy statements representing the political space covered by political parties. VAA designers face the challenge of coming up with policy statements in a short time frame. Even with medium-sized corpora of texts such as party manifestos, the formulation and selection of policy statements serving as a stimulus in the VAA is a tedious and time-consuming task. In addition, there is the risk of human selection bias. This study proposes a system to aid VAA designers in policy statement selection and formulation. The system uses the BERT language model with semantic similarity calculation to mine party manifesto sentences that are relevant to already existing VAA statements. For the experiments, VAA statements stemming from the 2021 elections and party manifestos issued for the previous two Japanese elections were used. To expand the policy space, VAA statements from the 2019 European Parliament elections were added. Results show that the proposed system is able to analyze large amounts of text in a short time, and mines text that provides practical support for designing and improving VAAs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.