Incremental computation of information landscapes for dynamic web interfaces
Vedran Sabol, Kamran Ali Ahmad Syed, Arno Scharl, Markus Muhr, Alexander Hubmann-Haidvogel · Human Factors in Computing Systems · 2010
This paper presents a technique for the visual analysis of topical shifts in dynamically changing textual archives. Our approach is based on the well-known information landscape metaphor, whereby topical changes are represented by changes in landscape topography. Incremental clustering and multi-dimensional scaling algorithms are periodically applied to a changing document set for generating a series of information landscapes. The resulting landscapes are suitable for dynamic Web interfaces, enabling the user to explore topical relationships and understand topical shifts and trends in changing document repositories.