Duration: 60 Minutes
Parts of Speech uses natural language processing of syntax to recognize, and tag parts of speech in a body of text. It provides users with the building blocks for looking at how phrases are constructed within each document in a content set. This tool effectively creates a lexicographical index or dictionary of a content set. The Gale Digital Scholar Lab’s Parts of Speech tool uses spaCy’s Parts of Speech Tagger model. In this session, you will learn how to run a Parts of Speech analysis and interact with the outputs. See how to compare different texts and make notes on the research process and findings. We review examples of when a researcher might perform a Parts of Speech analysis, and share considerations in cleaning the content set which would affect the results.