Text data can be extremely valuable given how much information humans communicate and store using natural language—the diverse set of data sources relevant to investment range from formal documents such as company statements, contracts, and patents, to news, opinion, and analyst research, and even to commentary and various types of social media posts and messages.

Numerous and diverse text data samples are available online to explore the use of NLP algorithms, many of which are listed among the references for this chapter.

To guide our journey through the techniques and Python libraries that most effectively support the realization of this goal, we will highlight NLP challenges, introduce critical elements of the NLP workflow, and illustrate applications of ML from text data to algorithmic trading.