This repository contains the material for the ‘Text-mining and Taylor’ workshop from AU Library at the Royal Danish Library.
The purpose of the workshop is to use a digital tool to survey larges bodies of text. In this case we will analyze all the song written by Taylor Swift. We will learn to make visualizations of the data, find out which words Swift uses the most and which emotional sentiment is linked to different albums.
The workshop focuses on tools from the coding program ‘R’ hosted in Posit.cloud. The main goal of the workshop is to create familiarity with the possibilities of using a digital tool for text mining and data visualization.
There are no expectations for previous experience with R, digital tools, or text mining.
There will be a hands-on exercise where participants use R, and code along with the workshop host.
The data for the workshop comes from the ‘taylor’ package in R, made by Jake W. Thompson. The package contains 3 datasets, which includes various data about Swift’s songs. The workshop will mainly focus on the ‘taylor_all_songs’ dataset, which for example contain data about album, track name, album release date and most importantly: lyrics.
