About me

• Automated Database Integration on huge databases
• Social Network Analysis on huge populations
• Knowledge Discovery in Databases, Ontologies, Data-Mining
• Natural Language Processing, Text Mining
• Military and Technology History

• My research area is currently on the extraction of facts from documents to create databases from them, re-purposed to secondary uses.

In many ways this is the extension of previous work on automated database integration, where the processes needed to move information back and forth between databases are discovered with little human intervention. Because of the complexity of the problem (different designs, database contents, bad documentation...) it has traditionally been solved through human review.

Middle-of-the-road methods are currently being investigated where routine, easily-mechanizable decisions are made algorithmically while ambiguous decisions are left for human review.

The applications of this research are the extraction of information from Great War archives and the creation of Social Network databases that support further research through collaboration with scientists in other fields.