This talk showcases the process behind turning a raw, difficult-to-parse dataset, collected over more than 40 years and spanning over 650 editions, into a working, interactive dashboard. Rather than a comprehensive AI tutorial or a deep dive into the underlying literary data itself, the talk centers on the decisions, obstacles, and problem-solving involved in building a usable research tool from a dataset decades in the making.

Siyang Ni will discuss how he used Claude and other AI tools throughout development, from designing a multi-stage pipeline to clean and validate decades of inconsistent records, to migrating everything into a PostgresSQL database, building an R Shiny interface to navigate and visualize results. Along the way, he'll reflect on what worked, what didn't, and how access to AI tools shaped his approach to a process to a project that would otherwise have demanded far more manual effort.

The project is a collaboration between Professor Anesko, PI and professor of English, Professor Isasi, director of the DLA Research Initiatives, and Siyang Ni, a Ph.D. candidate in the Department of Sociology and Criminology, supported by a C-SoDA grant (2025–2026).