TRIADS Training Series: Machine Learning for Text Analysis

In this 4-session series, we will cover the basics of how to use machine learning for text-analysis tasks in Python. Participants will learn how to create word embedding models, basic supervised models such as Random Forest and Logistic Regression, and unsupervised approaches such as k-means clustering. In the later sessions, we will cover how to use pre-trained large language models like BERT and GPT for zero-shot analysis (using the model with no additional training), and how to fine-tune a pre-trained model for your own text-analysis needs. Participants must have confidence in the basics of Python syntax, as well as familiarity with basic text-analysis methods (such as tokenization and word frequency analysis)

This class will be fully in-person, and participants will use their own laptops.

TRIADS training workshops are co-sponsored by University Library Data Services, as part of the DataLab Workshops series.

Time: Mondays and Wednesdays, 11.30-1pm

Location: Instruction Room 3, Olin Library Level A

Instructor: Claudia Carroll

Max enrollment: Enrollment is limited to 20. If you enroll and elect not to attend, please let us know ASAP so we can offer the space to another participant.