This sessions will introduce participants to a lightweight tool for large-scale text analysis of documents in PDF format, enabling the user to discern distinctive features of a textual corpus, such as topics, locations, and personal names. Participants will be able to:
- recognize whether or not the text of a PDF can be read by computers
- create quality metadata for items in their Zotero library
- create visualizations of large collections of items in their Zotero library using Paper Machines
- frame a research question that visualizations created using Paper Machines could help to answer
This session will appeal to humanities scholars with minimal computational skills interested in seeing texts in new ways.