Introduction to Text Mining and NLP for Health Data
February 12 @ 10:00 am - 12:00 pm
Registration is required. You will receive a confirmation once you are accepted into the workshop and a communication with the workshop materials and Zoom links.
This workshop is open to all members of the UC Davis community. DataLab Affiliates receive priority registration.
This workshop covers an introduction to natural language processing (NLP) and caveats for its application to health data. Using the R programming language we will introduce the basics of text processing and demo how to calculate common metrics including word frequencies, term frequency-inverse document frequency (TFIDF), and principal component analysis (PCA) to explore important words and group similar documents. We will also introduce more advanced NLP topics (sentiment analysis, topic modeling, etc.) and discuss classical versus deep learning approaches, as time permits. Learners with proficient R skills are encouraged to code along.
* explain natural language processing in lay terms
* give examples of text mining and NLP applications for research
* evaluate particular challenges posed by working with health data
* describe key text mining and NLP metrics for assessing word importance and document similarity
* identify where to go to learn more!
No prior NLP or text mining knowledge is necessary. Learners interested in coding along are expected to have prior experience using R, be comfortable with basic R syntax, and to have it pre-installed and running on their laptops. Some preparatory reading prior to the workshop may be provided.