With Data Scientist consistently named one of the trendiest jobs of the 21st Century, it’s no surprise that many are flocking to learn skills like Python, mathematics, and machine learning. In this tutorial we’ll introduce attendees to an important subfield of data science: natural language processing (NLP).
Using popular data science libraries such as pandas, spaCy, and scikit-learn, we’ll cover common NLP terminology used in the industry as well as text preprocessing techniques. In addition, we’ll identify real world objects like people and businesses using named entity recognition and summarize data using term frequency. We’ll also learn to analyze the structure of our text data using dependency parsing and part-of-speech tagging. We'll end with an introduction to text similarity and determine key topics using topic modeling.
Attendees will gain hands-on experience by analyzing 500 Amazon Home and Kitchen product reviews.