LUCDH Workshop - An Introduction to Text Mining in the Humanities
- Friday 25 September 2020
2311 BD Leiden
- Kaltura online
Studium Digitale: An Introduction to Text Mining in the Humanities
NB This workshop was postponed from March 27 to September 25 online due to Covid restrictions. If you wish to receive PP slides from the presentation, and/or links to RapidMiner and Python tutorials - please email firstname.lastname@example.org
Studium Digitale is a workshop series organised by the Leiden University Centre for Digital Humanities that provides introductory or advanced knowledge on digital tools that benefit humanities research. The upcoming workshop will explore tools for text mining and machine learning and is taught by Alex Brandsen (Leiden University, Faculty of Archaeology).
A lot of humanities research uses text data, and being able to automatically analyse these texts is often of great benefit. In this workshop, you will learn the basics of using machine learning for text mining, using the free tool RapidMiner. We will first inspect the data, clean the data, create a word cloud, and finally perform sentiment analysis on a collection of Tweets.
Please note that for the sentiment analysis (part 1), you will need to bring your own laptop. If possible, please install RapidMiner before the workshop (choose the 30 day trial license).
A second (optional) part of the workshop is to work with Python and Jupyter notebook to perform distant reading of English children's literature 1789-1914 for the representation of insects and other creepy crawlies.
Both parts are aimed at beginners, and we assume you have no previous knowledge of coding or machine learning.
The max number of participants is 15, and places fill quickly. Please register by sending an email to email@example.com. You will receive confirmation of your place (or a place on the waiting list.)