Introduction to Text mining
In this hands-on workshop, we will analyse/mine texts using a couple of basic techniques and available tools. It includes: - extracting (named) entity references from running text - classifying text types (e.g. newspaper article vs novel vs letter) - topic modelling - determining quality of OCR'd text using dictionaries Leiden University Libraries started the Centre for Digital Scholarship in 2016, with supporting researchers in using text and data mining among its core services. This workshop is based on existing openly licenced materials and (growing) experience in supporting digital humanities research at Leiden University (in The Netherlands).
