Revisiting the 'Donation of Constantine'

Abstract

Techniques developed for synchronic text classification problems are applied to a significantly diachronic dataset. The scale of the temporal categories appears to matter. The problem addressed is that of using automated text classification methods to temporally locate The Donation of Constantine. The results reported do not contradict the analysis of Lorenzo Valla from 1440, claiming the document a forgery, but suggest that it is a very good forgery. This contributes to establishing the validity of these classification methods as applied to temporal categories and small datasets.