Text mapping: Visualising unstructured, structured, and time-based text collections

Large collections of text documents are increasingly common, both in business and personal information environments. Tools from the field of information visualisation are being used to help users make sense of and extract useful knowledge from such collections. Flat text collections are often visualised using distance calculations between documents and subsequent (distance-preserving) projection. Distance calculations are often based on a vector space of term vectors. Projection is often achieved with a force-directed placement algorithm. Where extra information about a text collection is available, such as a topical hierarchy or some chronological ordering, it can be used to improve a visualisation. This paper gives an overview of text mapping techniques.