This will be related to the broader visualisation literature, with a special focus on the characteristics of the users. It does so by discussing what it is that VAAs want to visualise and what the underlying assumptions regarding the visualisation are. This study aims to give a first start by reviewing the different visualisation techniques VAAs use and the critiques that have been raised against them. This is important in light of the continued interest in unequal political participation as it suggests that VAAs may, in the long term, be able to reach groups in society currently not engaged in the political process.ĭespite the fact that the visualisations VAAs provide to the user to show their match with the included parties or candidates constitutes one of the major attractions of VAAs to users, this part of VAA design has until now rarely been studied. A development which corresponds to Rogers’ diffusion thesis. Overall, we have thus seen a development in which users become more similar to the population as a whole. Political interest remains an important predictor of VAA usage. Those with the highest levels of education remain significantly more likely to use VAAs, but this is no longer true for those with moderate levels of education. Age remains important, while gender is no longer significant. Using German election data, it measures whether age, gender, education, and political interest still explains VAA use.
For the first time, this article assesses whether this pattern changes over time. The early VAA literature found that VAA users tend to be young, well-educated, politically interested men. As the popularity of VAAs increases and research corroborates their effect on turnout and political preferences, it matters at lot who uses VAAs and, thus, experiences these effects. VAAs match the opinions of voters with those of candidates or parties. Voting advice applications (VAAs) are one prominent attempt. Unequal and declining electoral turnout has spurred numerous initiatives to reverse the trend. Results obtained from multiple experiments show that, although the general maximum F1 value is 0.4, T2S can correctly predict the stance with a general minimum MAE of 1.13, which is a great achievement considering the task complexity. Interestingly, T2S can be applied to any social media user for any context of interest, not limited to the political one. To this end we propose Tweets2Stance (T2S), a novel and totally unsupervised stance detector framework which relies on the zero-shot learning technique to quickly and accurately operate on non-labeled data. Starting from the knowledge of the agreement level of six parties on 20 different statements, the objective of the study is to predict the stance of a Party p in regard to each statement s exploiting what the Twitter Party account wrote on Twitter. The ground-truth user's stance may come from Voting Advice Applications, online tools that help citizens to identify their political leanings by comparing their political preferences with party political stances. The work herein described focuses on a completely unsupervised stance detection framework that predicts the user's stance about specific social-political statements by exploiting content-based analysis of its Twitter timeline. The recent research perspective exploits the fact that a user's political affinity mainly depends on his/her positions on major political and social issues, thus shifting the focus on detecting the stance of users through user-generated content shared on social networks. Existing approaches, mainly targeting Twitter users, rely on content-based analysis or are based on a mixture of content, network and communication analysis. In the last years there has been a growing attention towards predicting the political orientation of active social media users, being this of great help to study political forecasts, opinion dynamics modeling and users polarization.
0 kommentar(er)
