Personal information management through interactive visualizations

The PhD thesis presented in this paper tackles the personal information overload phenomenon. Our purpose is to offer a set of interactive visualization techniques allowing one’s personal digital memory to be organized and overviewed. This system will provide easy browsing, guiding towards the wanted piece of information and allow a free exploration of the personal information space. Three main axis of research are involved: (1) cross-media mining to generate indexes and alignments, (2) data clustering to organize personal information and (3) information visualization techniques, that should provide means to easily navigate through the personal information space. In this paper, we present our approach to these challenges using the personal email archive as an entry point into the personal information space. Indeed, we believe that emails are a particularly rich source of metadata for indexing personal information, as well as a representative subset of the whole personal information space. We finally present the work done during the first year of this PhD thesis and the roadmap for the future.