This workshop will introduce participants to some essential methods and techniques used for computational text analysis. We will explore the difference between "text mining" and "text analysis," as well as discuss common text processing tasks such as tokenization and computing term and document frequencies (TF-IDF). Finally, we will look at some natural language processing methods such as named entity recognition, sentiment analysis, and topic modeling.

No prior experience with text mining or analysis is required; all are welcome to attend - bring your questions and ideas! The workshop will also introduce some recommended tools and learning resources for getting started with text analysis, including a hands-on demo of Voyant Tools (https://voyant-tools.org/). 

Can't make it to this workshop? You can always contact us with your questions about this or other digital scholarship and publishing topics! Read more about Digital Scholarship & Publishing support.

Location: This event will take place in Hillman Library's Digital Scholarship Lab (room G30), located just past the main service desk on the ground floor of the library. Look for the glass double-doors after entering through the ground floor atrium entrance; if you enter on the first floor, take the elevator down to the ground floor and turn right out of the elevator.

Software: The Digital Scholarship Lab computers have relevant software for this workshop available (unless we are using software that is otherwise available online). Non-Pitt participants must obtain a temporary ID at the Hillman circulation desk to access the computer workstations. Please check in with the workshop presenter or contact ULS-DigitalScholarshipServices@pitt.edu if you plan to bring your own personal laptop and have questions about downloading software prior to attending the event.