Abstract
In the process of statement selection for online voting advice applications (VAAs) a considerable amount of time is spent for analyzing the domestic and foreign policies of a given country. However, harnessing large amounts of available open data, which would be useful in this design process, manually is impractical. In order to facilitate such time-consuming and labor-intensive work, the authors propose a system to assist VAA designers formulating policy statements. Using advanced language modeling and text summarization techniques and based on open government data related to politics during the legislature preceding an election, the system produces suggestions applicable for revising or creating new VAA policy statements. Experiments conducted on VAA and e-petition data from Taiwan show that the proposed system can generate meaningful suggestions for VAA designers and could therefore help reducing the cost of the VAA design process.
Buryakov, Daniil