An Introduction to Text Mining with Python

In this repository you will find all the materials used in the Introduction to Text Mining, part of the Text Analysis module of the MSc in Digital Scholarship (University of Oxford, Michaelmas Term 2023).

Overview page

General info on HackMD.

Notebooks

Day 1

• Python basics
• Mining Dickens. Part I: Off-the shelf NLP tagging and quantitative data exploration

Day 2

⚠️ Note: the following notebook takes up too much memory on Binder. Please use Google Colab instead.

• Mining Dickens. Part II: Topic modelling, sentiment analysis and character network analysis

Day 3

• Introduction to Word2Vec

Note: the following would require you to download the embedding models from here.

• Detecting semantic change in Word2Vec models: changepoint detection

Binder

On MyBinder: