Skip to Main Content
The process of voting for a candidate involves selecting an individual who best matches a personal system of values and beliefs. Typically, voters must select a candidate whom they believe fits their issue stances best by determining their approximate similarity to the candidates on the issues, and cognitively positioning themselves amongst the candidates. We show in the context of our candidate position data that the intrinsic dimensionality of candidate similarity in our data can be sufficiently expressed algorithmically in two dimensions using Gower similarity and Sammon mapping. A participant study analyzes how voters choose to position themselves on this low dimensional representation, and how this positioning is related to the position dictated by their actual responses to issues, as well as to their general political stance.