In this workshop, you’ll learn how to use pre-trained open source tools for document classification and sentiment analysis. Rather than building custom models from scratch, you'll explore how to apply existing models using libraries like Hugging Face's Transformers and SpaCy. You’ll gain experience in working with these tools to process text data and perform classification or sentiment analysis with minimal setup. This session will show you how to effectively apply pre-trained models for text analysis tasks.

Note: This workshop will be offered in person at the UCSF FAMRI Library at Mission Bay and online through UCSF Zoom. You will receive an email from LibCal with room information and Zoom link prior to the start of the workshop. 

Workshop Series: Data and Document Analysis with Python, SQL, and AI

This series is designed for researchers, staff, and students who want to learn Python from the ground up, focusing on data analysis, document analysis, and AI-based research. Throughout the workshops, we’ll dive into various data types—including numerical data, health data, text, and images/videos—and explore analysis techniques like regression, classification, and sentiment analysis. We’ll put a particular focus on text analysis, especially analyzing documents from our industry document library.

As programming evolves, so does the way we learn it. While we’ll introduce AI-assisted programming earlier in the series than in past workshop series, we’ll still start with the basics. The early workshops (Intro to Python Parts 1 & 2 and Intro to SQL) will use AI sparingly. As the series moves forward, we’ll dive into topics like web APIs, text analysis, natural language processing, machine learning, regression, document analysis, and AI system interaction, with more AI-driven techniques along the way.