Sociomapping

Sociomapping is a method developed for processing and visualization of relational data (e.g. social network data). It is most commonly used for mapping the social structure within small teams (10-25 people). Sociomapping uses the landscape metaphor to display complex multi-dimensional data in a 3D map, where individual objects are localized in such way that their distance on the map corresponds to their distance in the underlying data.

Thanks to its visual coding Sociomapping engages our evolved skills for spatial orientation and movement detection, thus making the interpretation of complex data easy and accessible for everyone.

The sociomapping method was developed in 1993-1994 by R. Bahbouh as a tool that would facilitate understanding of data about social relations and help preventing conflicts within teams of military professionals. The first major application of sociomapping took place in 1994-1995 during the HUBES experiment (Human Behavior in Extended Spaceflight) – a 135-day-long simulation of a spaceflight with three crew members organized by European Space Agency. Sociomapping was then regularly used in other spaceflight simulations (1995-1996: EKOPSY, 1999: Mars105, 2010-2012: Mars500). Since 2005, sociomapping has been extensively used in business environment to analyze relationships within senior management teams. In 2012, C. Höschl jr. developed Real Time Sociomapping® software that enables customers to do team sociomapping on the spot and is used for commercial purposes.

The basic principle of Sociomapping is transforming original data concerning a set of objects in such a way that the distance of each pair of objects on the map corresponds to the distance between the two objects in the underlying data. Transformation of the data is a matter of 1) choosing some metric that could be reasonably interpreted as distance, and 2) translating the multi-dimensional distance matrix into 2D coordinate system so that the correlation between map-distances and data-distances is maximized. The algorithm for data-transformation, developed by C. Höschl jr., is thus a dimensionality-reduction technique, such as PCA, and its goodness of fit can be measured by Spearman correlation between the map-distances and data-distances. Sociomapping takes into account that, particularly in case of social relations, relational data may be asymmetrical (e.g. John like Mary more than she likes him) and preserves this information by mapping the objects in such a way that for each object the closest other object is the one closest to it according to the metric of choice in the underlying data, and so on for other objects ordered by distance.

...
Wikipedia