Visual Community Detection: An Evaluation of 2D, 3D Perspective and 3D Stereoscopic Displays\ud

摘要

3D drawing problems of the 90s were essentially restricted on representations in 3D perspective. However, recent technologies offer 3D stereoscopic representations of high quality which allow the introduction of binocular disparities, which is one of the main depth perception cues, not provided by the 3D perspective. This paper explores the relevance of stereoscopy for the visual identification of communities, which is a task of great importance in the analysis of social networks. A user study conducted on 35 participants with graphs of various complexity shows that stereoscopy outperforms 3D perspective in the vast majority of the cases. When comparing stereoscopy with 2D layouts, the response time is significantly lower for 2D but the quality of the results closely depend on the graph complexity: for a large number of clusters and a high probability of cluster overlapping stereoscopy outperforms 2D whereas for simple structures 2D layouts are more efficient.\ud