NOTE: This event is availble to all University of California affiliates and ADHHI scholars. Please register using your university email address if you have one. 

This workshop will introduce document classification and sentiment analysis using Python and Scikit-Learn. Participants will learn how to build, train, and evaluate a custom supervised machine learning classifier to predict the topic and sentiment of text documents. 

This workshop is part of a broader series covering programming for the digital humanities, with an emphasis on document and text analysis. Although these workshops do not have any formal prerequisites, some background in Python and SQL would be helpful. These workshops will build on material from previous sessions, so it is recommended but not requred to take the workshops in sequence. 

Registration Links: 

• Data Analysis with Python and SQL, Part 1:
  • https://calendars.library.ucsf.edu/event/12900575
• Data Analysis with Python and SQL, Part 2:
  • https://calendars.library.ucsf.edu/event/12901228
• Reading Data from APIs with Python:
  • https://calendars.library.ucsf.edu/event/12901233
• Image, Audio, and Video to Text Transcription with Python:
  • https://calendars.library.ucsf.edu/event/12901235
• Python Background for Text Analysis and Natural Language Processing:
  • https://calendars.library.ucsf.edu/event/12901494
• Document Classification and Sentiment Analysis using Python and Scikit-Learn
  • https://calendars.library.ucsf.edu/event/12901511
• Document Topic Modeling with Python
  • https://calendars.library.ucsf.edu/event/12901514
• Classification, Sentiment Analysis, and Topic Modeling using Cloud Based APIs:
  • https://calendars.library.ucsf.edu/event/12901513

Note: This workshop will be offered online through UCSF Zoom and in person at the UCSF Famri Library at Mission Bay. All registrants will recieve an email from libcal with location information and a Zoom link prior to the start of the workshop. You will have the option to attend in person or online regardless of how you register, so please just select the option you think is most likely at the time of registration.