Determining Writership of Historical Manuscripts using Computational Methods

The role of computational methods in the determination of authorship of historical manuscripts is considered. During the last few years the computational forensics community has developed automation tools for forensic document examination, in particular for determining whether a given handwriting specimen can be attributed to known writing. We describe how these methods can be used with historical manuscripts where authorship is obscure or disputed. As an example the task of determining writership of a manuscript known as the Hydrachos manuscript (the questioned document) is considered. Testing the hypothesis whether it is attributable to an important American writer (Herman Melville) is described. The questioned document is compared against handwriting samples of Herman Melville, a 19th century American author who has been hypothesized to be the writer as well as against samples crafted by several writers from the same time period. The comparison led to a high confidence result to the questioned document’s writership, as well as gives evidence for the validity of the writer verification method in the context of historical documents. Such methodology can be applied to many such questioned historical documents, both in literary and legal fields.