Operation Debunker (GA DSI Capstone)
Please note that this repository represents an early stage in the development of the idea. You can find an in-progress version here
Spurious quotations present an interesting stylometric problem in author analysis. Where most disputed texts are lengthy (see, e.g., the Federalist Papers), a quotation is short, usually only a few hundred characters, which provides limited sampling. Furthermore, although a writer develops a style over time, written style and spoken style can differ greatly. This project attempts to answer the question of whether it is possible to identify a spurious quotation based on text alone.