The empathic visualisation algorithm (EVA) - an automatic mapping from abstract data to naturalistic visual structure

Abstract

This paper demonstrates a technique for visualising multidimensional data sets holistically. The EVA algorithm provides an automatic mapping from semantically important features of the data to emotionally or perceptually significant features of the corresponding visual structure (such as a face). In other words a single glance at the visual structure informs the observer of the global state of the data, since the visual structure has an emotional impact on the observer. The visualisation is designed to correspond to the impact that would have been generated had the observer been able to access the relevant semantics of the underlying data.

Anthropomorphic visualization

“…Our approach attempts to learn from past critiques of Chernoff faces. For example, if the data values that change the expression of the face are arbitrarily mapped to the various facial features, the visualization may lead to a distorted face that has an unexpected emotional impact on the viewer and can be hard to decipher [5]. With our design, we are not depicting individual facial features completely independently, but instead have a set of templates for particular facial expressions, which can be varied based on a set of values such as responsiveness and intensity while still maintaining the overall sense of the emotion represented.…”