Contextual search and analysis of pest and nuisance species through time
in the KB newspaper collection
Historically, some animals have been perceived as threats by humans. These species were believed to carry diseases or harm crops and farm animals. SERPENS aims to study the historical impact of pest and nuisance species on human practices and changes in the public perception of these animals.
The KB newspaper collection will be primary source of information to study this. The first impediment lies in accessing the KB collection: keyword search cannot smoothe spelling variations, vernacular vs. Latin names or the fact that many vernacular animal names can refer to other things (e.g. surnames).
To remedy this, the WP2-3 diachronic lexicons will be used for query expansion in combination with topic modelling to filter out irrelevant results.
Furthermore, instead of returning documents as search results, which are difficult to compare and analyze, we will create a database containing core information for studying human-fauna relationships by employing the WP3-Semantic-Parsing-Dutch tools.
KNAW Humanities Cluster
Marieke van Erp, Thomas van Goethem, Katrien Depuydt and Jesse de Does (2017) Towards Semantic enrichment of Newspapers: A Historical Ecology use case. Proceedings of Workshop on Humanities in the Semantic Web – WHiSe II. Vienna, Austria, 22 October 2017.
Marieke van Erp, Jesse de Does, Thomas van Goethem and Katrien Depuydt (2018) Good lynx, bad lynx: document enrichment for historical ecologist. Presentation at Computational Linguistics in the Netherlands (CLIN 28). Nijmegen, the Netherlands, 26 January 2018.
Community workshop "Historische Kranten als Bron voor Onderzoek naar Exoten"
Rob Lenders: Introductie
Thomas van Goethem: Op jacht naar de bunzing en de lynx: twee voorbeelden uit de KB-krantencollectie