Text classification is a broad field covering an array of topics, for example determining if a newspaper article is from the sports page or not. In this workshop we will go through the fundamental steps like tokenization and then proceed to completing tasks such as creating a spam filter. These techniques use machine learning but no prior machine learning knowledge is necessary for this workshop. We will primarily be working with the package NLTK. Fundamental knowledge of python is helpful but not mandatory for this workshop. Please bring your laptop.