From Sentiment Mining to Mining Embodied Emotions
Emotional styles on the Dutch stage between 1600-1800
Imagine we would have a search engine linking data of over 75.000 Dutch historical people. Which relations would we be able to reveal between people and events, geographical movements and networks between people? What do they tell historians about the formation of Dutch society and the ‘boundaries of the Netherlands’? How did the current Dutch elite develop from the colonial past?
The use of biographies in academic theories and methods is by some still not considered as a worthy academic discipline, being too anecdotal and limited. But as Brian Harrison stated in 2004: “…when the capsule biography of an individual is combined with 50.000 others, many of them relatively obscure, […] and when they are all powerfully searchable online, the social historian’s grumbles about biography’s limitations as an approach to historical study dissolves into nothingness.”
It is the ‘Art and Science of History’: Drawing up a narrative from primary and secondary sources which approximates historical reality as well as possible. The only way to falsify presented historical facts is by going back to the original source(s) and look at those source(s) critically. Therefore, it is important to know exactly what information comes from where. On the website of the Dutch Biography Portal you can find scientific information about various leaders and other prominent figures from Dutch history; from the earliest times up to the present day. The website is constantly replenished with new information and images. Working with the Dutch Biography Portal involves studying complex data that is incomplete and ‘noisy’. This project aims to enhance the potential of the Dutch Biography Portal by transforming the available data into a semantic knowledge base.
BiographyNet’s multidisciplinary team combines expertise from history, computer science, and computational linguistics. A generic text mining tool will be developed that converts textual data into structured data. An easy-to-use interface will be developed that will inspire historians to undertake new research and give direction, rather than being the ‘closing factor’ in their research.
Ultimately, the project may help to reveal unknown relations between people and events by linking data that has mainly been studied in isolation so far.