Paper Machines works with the individual researcher’s own hand-tailored collections of texts, whether mined from digital sources like newspapers and chat rooms or scanned and saved through optical character recognition (OCR) from paper sources like government archives. It can allow a class, a group of scholars, or scholars and activists together to collect and share archives of texts.

They also draw upon a rich heritage of computational history, stretching back to early cutting-edge work done with censuses in the 1960s.