BiographyNet: Extracting Relations Between People and Events

Humans are often called the smallest units of history. Any historical event can be traced back to the acts, decisions and thoughts of individuals. Simultaneously, these individuals share a lot of common character traits. They were born, have parents, most go to school, some have siblings, they died or will die and many of them have a career of some sort. The most famous individuals also have a ‘claim to fame’, which can range from being a famous politician to having murdered 27 people. The World Wide Web contains a massive amount of biographical data that begs to be analyzed with computational methods. Part of this biographical data is already (semi-)structured and is readily available for systematic computerised analyses. For this reason many projects analyzing biographical digital data have recently been undertaken.1 BiographyNet is one of these projects. BiographyNet is a digital humanities project (2012-2016) that brings together researchers from history, computational linguistics and computer science.2 The project uses data from the Biography Portal of the Netherlands (BPN), which contains approximately 125,000 biographies from a variety of Dutch biographical dictionaries from the eighteenth century until now, describing around 76,000 individuals.3 BiographyNet’s aim is to strengthen the value of the portal and comparable biographical datasets for historical research, by improving the search options and the presentation of its outcome, with a historically justified NLP pipeline that works through a user evaluated demonstrator. The project’s