TRIADS Training Workshop: Machine Learning for Sentiment Analysis

This single session workshop aims to introduce participants to machine learning methods for sentiments analysis. Sentiment analysis is a research method that aims to classify text in terms of its emotional valence, such as the degree to which it is positive or negative, or what emotions the text is conveying (happy, worried, angry etc.) In the last few years, machine learning approaches have displaced rules-based dictionary methods as the state-of-the-art for sentiment analysis. The process involves providing training data annotated according to the sentiment categories a researcher wants to measure in a text, and training a language model to assess those categories in a dataset. This workshop will train participants in how to analyze a text-based dataset using pre-trained sentiment analysis models, using the Python programming language. This workshop is aimed at graduate students, faculty and staff who use large text datasets in their research. Participants are encouraged to bring their own text corpus to the class. Participants should be comfortable with basic functions and libraries for text analysis in Python, such as NLTK and Spacy. Participants should also be able to work in Jupyter Notebooks.

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: Monday, 12:00 - 2:00 p.m.

Location: Olin Library Instruction Room 1

Instructor: Claudia Carroll

Max enrollment: Enrollment is limited to 30. If you enroll and elect not to attend, please let us know ASAP so we can offer the space to another participant.