• 2005
• Domain Map
• Exhibit map
• Project link

Dr. André Skupin is an Associate Professor of Geography at the San Diego State University. His research interests focus on geographic visualization, visual data mining, and information visualization. This map is a visualization derived from more than 22,000 abstracts submitted to the Annual Meetings of the Association of American Geographers during a ten-year period from 1993 to 2002. The methodology is centered around the representation of each document as an n-dimensional vector of terms. These vectors are used to construct a neural network model of the geographic knowledge domain using a Self-Organizing Map (SOM). The neural network model is then transformed into two types of information: (1) a landscape in which elevation indicates the degree to which a single, focused topic is addressed; and (2) multilevel text labels associated with regions in the visualization. The final rendering was executed in standard geographic information systems (GIS) software.

Description of Unique Features: The most unique aspect of this visualization is its combination of intense computation with geographic metaphors and cartographic design considerations. From a computational perspective, the use of a self-organizing map consisting of a large number of neurons (10,000) is fairly unique. The final map presented here aims to explore how far we can go in the design of map-like information visualizations. Its use of a range of label sizes (from very large to very small) on a large-format map and the omission of a legend are aimed at challenging traditional notions of interactivity, by encouraging viewers to vary their distance from the map and instigating discussion.

Visual Perception or Design Principles Applied: Cartographic design principles were used throughout.

Cognitive Principles or Metaphors Employed: Geographic and cartographic metaphors.

Data Used: A database of abstracts submitted to the Annual Meetings of the AAG held between 1993 and 2002.

Data Analysis Techniques Applied: Vector-space modeling, with the documents represented as n-dimensional vectors.

Spatial Layout Techniques Applied: Self-organizing map (SOM)