Identifying, measuring and visualising the evolution of a story: A Web mining approach

Rich information spaces (like the space of scientific publications or the Web) are full of a higherorder type of ”stories”: sets of statements that evolve over time, manifested as, for example, sequences of scientific papers on a topic, collections of newspaper articles reporting events relating to an evolving crime investigation, or sets of news articles and blog posts accompanying the development of a political election campaign. In this paper, we propose a method and a visualisation tool for mapping and interacting with such stories. In contrast to existing approaches, our method concentrates on relational information and on local patterns rather than on the occurrence of individual concepts and global models. A real-life case study is used to illustrate the method and tool.