Social Voting Advice Applications—Definitions, Challenges, Datasets and Evaluation

Abstract

Voting advice applications (VAAs) are online tools that have become increasingly popular and purportedly aid users in deciding which party/candidate to vote for during an election. In this paper we present an innovation to current VAA design which is based on the introduction of a social network element. We refer to this new type of online tool as a social voting advice application (SVAA). SVAAs extend VAAs by providing (a) community-based recommendations, (b) comparison of users' political opinions, and (c) a channel of user communication. In addition, SVAAs enriched with data mining modules, can operate as citizen sensors recording the sentiment of the electorate on issues and candidates. Drawing on VAA datasets generated by the Preference Matcher research consortium, we evaluate the results of the first VAA-Choose4Greece-which incorporated social voting features and was launched during the landmark Greek national elections of 2012. We demonstrate how an SVAA can provide community based features and, at the same time, serve as a citizen sensor. Evaluation of the proposed techniques is realized on a series of datasets collected from various VAAs, including Choose4Greece. The collection is made available online in order to promote research in the field.

The Effect of Voting Advice Applications on Political Knowledge and Vote Choice

“…For example, in a deliberative democracy citizens should be able to find each other online in order to discuss how current political issues can best be solved. Hence, from the perspective of this different model of democracy, a very different type of VAA would probably have to be developed in order to stimulate a well-functioning democracy (see Fossen & Anderson, 2014, for further suggestions; for descriptions of VAAs that include a networking element, see Katakis et al, 2014).…”

A normative set of criteria to increase political competence through voting advice applications

“…A VAA making an aggregation in which the different policy issues cannot be disentangled will hardly be accountable. This is the case of the Support Vector Machine and the Neural Network Machine used by [Katakis et al, 2014]. In these proposed methods of recommendation, it is not possible to clearly evaluate the relationship between the recommendation and the policy issues.…”

Statistical Inference with Data Augmentation and Parameter Expansion

“…From ( 4),( 8) and ( 9) it follows that the upper bound on the sum of error probabilities in (7) for the expanded model is smaller than that of the original model.…”

“…We study initially the problem of obtaining representative information for the population, from a large number of non-representative population's units with a common attribute, A. This attribute could be, e.g., an account in Facebook or following a celebrity in a Social Network; the latter occured in practice with Social Voting Advice Applications (Katakis et al, 2014).…”