Text mining is a workflow that aims to automatically detect meaningful patterns and relationships in text with the help of a computer. It is being used in many diverse settings: identify trends in social media, explore narratives in literature and historical discourse, and to discover drug–drug interactions in medical texts.

This tutorial aims to give an introduction to practical methods for analysing text using natural language processing methods. We will illustrate a few tools, resources and workflows, including word embeddings, text clustering and binary text classification.

The tutorial uses the cloud-based Google Colaboratory which lets you write and execute code, save and share your analyses, and access powerful computing resources, all from within a browser. You will need a Google account.

For info and applications, contact Johan Frid.