Fused Exploration of Temporal Developments and Topical Relationships in Heterogeneous Data Sets

Abstract

In many application areas which deal with heterogeneous data sets temporal developments and topical relationships both play an important role. A number of visual representations have been developed which separately address each of these two aspects of the data. However, a simultaneous analysis of both aspects is also often required. In this paper we introduce an approach which utilizes a combination of visual representations, where some are targeting the temporal behaviour while others are focusing on topical relationships. The views are fused in the sense that they are tightly coupled with respect to the visualised data set, considered time interval, and user actions. The resulting user interface enables the user to simultaneously explore and discover patterns in both temporal and topical aspects of a heterogeneous data set. As a proof of concept a demo application was developed and applied for visualising temporal and topical patterns extracted from meeting recordings.