A tag-based network analysis of the Epstein Files through statistical validation
The Epstein files were released as a massive dump (over 300 GB) of PDFs, comprising document scans, emails, and photos. We delved into this jungle of data and extracted a bipartite network that links each person named in the files to the documents in which they appear. Using a procedure called "statistical validation", we then built a network of these people, connecting them whenever their co-occurrences could not be explained by chance alone. We also tagged each person according to seven key themes present in the files. In this presentation, we will navigate this network, explore its community structure, and analyze how the thematic tags are distributed across it.
This Annual PhD student seminar will be broadcasted in the following zoom link: https://us06web.zoom.us/j/89027654460?pwd=Wg9TYMPqqP2ipfj2JVvEagmzaTw29c.1
Contact details:
Tobias Galla Contact form