Please attend one of the iterations of the “Text Analysis with R” sessions before attending this workshop. If you cannot attend the prerequisite, contact Sarah Stanley for the slides and some test exercises to try before attending this session.

In this session, we will look at a large corpus of documents to determine the “topics” that are prevalent in those documents. We will train a few different models, to show how topic modeling methods like LDA can be highly subjective. We will also take the topic models we have created and analyze them against the individual documents to show how each topic occurs in each document. This session requires some familiarity with R, so please attend one or two of the previous sessions, or contact Sarah Stanley.

Please bring a laptop to this session, and have R and RStudio installed, following the instructions in this LibGuide: https://guides.lib.fsu.edu/text-analysis/r/installation. Before attending, please install the “topicmodels” and "tm" packages in R, by going to R > “Install packages” in RStudio. If you have problems with installation, or if you do not have access to a laptop, please contact Sarah Stanley prior to the session.