Starting with a short introduction to recent innovations in natural language processing (NLP), Dr. Andrew Janco outlines what new methods in applied NLP have revealed in the records of Prozhito, a crowd-sourcing project that has transcribed more than 3,000 Russian-language diaries. What patterns appear when studying the collection at scale? What new questions can we ask? What answers are does the collection bring to existing debates?
Andrew Janco is a Digital Scholarship Librarian at Haverford College. He completed his Ph.D. at the University of Chicago and held post-docs at the University of Chicago's Pozen Family Center for Human Rights and the Human Rights Institute at the University of Connecticut. He recently completed his M.S. in Library and Information Science at the University of Illinois Urbana-Champaign.
Dr. Janco has a passion for inquiry-driven and community-engaged digital projects. He is one of the lead developers working on a digital archive and research application for the Groupo de Apoyo Mutuo; Guatemala's oldest human rights organization. He also works on applied machine learning for Humanities and Social Science research.