It can be considered a form of style-based document authentication (Echtheitskritik), which has valuable applications that extend well beyond the domain of literary analysis, esatto, for instance, the domain of forensic sciences. According preciso Stamatatos’s 2009 survey of the field, ‘[t]he main idea behind statistically or computationally-supported authorship attribution is that by measuring some textual features we can distinguish between texts written by different authors.’22 22 E. Stamatatos, ‘A survey’ (n. 14, above) 538. This basic assumption implies that it should be possible puro assess, for any new unseen document, whether or not it was written by other authors for whom we have texts available. Nowadays computational authorship studies are often considered a subfield of stylometry sopra the digital humanities, the broader computational study of the writing style of texts.23 23 D. Holmes, ‘The evolution of stylometry sopra humanities scholarship’, LLC 13 (1998) 111–17.
While stylometry has verso rich history, dating back onesto at least the nineteenth century, it is clear that it received its most important impetus only durante the past two or three decades, stimulated by the rise of (personal) computing and the increased availability of large bodies of text durante electronic form. Apart from the influential, yet more conventional, statistical analyses carried out by pioneers such as Mosteller and Wallace or John Burrows well before the 1990s, an influential approach mediante authorship studies has been puro approach the attribution of anonymous texts as verso ‘text categorization’ problem.24 24 Mosteller and Wallace, Inference and disputed authorship (n. 4, above) and J. Burrows, Computation into criticism: verso study of Jane Austen’s novels (Oxford 1987). Heavily influenced by parallel research sopra computer science, the idea was onesto optimize verso statistical classifier on example texts by a number of available candidate authors, much like verso spam filter nowadays is still trained on manually annotated emails puro learn how sicuro distinguish between ‘junk’ email and normal messages.25 25 F. Sebastiani, ‘Machine learning sopra automated text categorisation’, ACM Cervello elettronico Surveys 34 (2002) 1–47. After preparazione such a classifier on this example momento, the classifier could then be used puro categorize or classify anonymous text as belonging puro one of the istruzione authors’ oeuvres.
It resembles per police lineup, in which the correct author of an anonymous text has puro be singled out from a series of available candidate authors for whom reference or ‘training’ material is available
This text categorization setup is commonly known as ‘authorship attribution’.26 26 The following paragraph heavily draws on M. Koppel and Y. Winter, ‘Determining if two documents are written by the same author’, JASIST 65 (2014) 178–187. For a number of years, practitioners of stylometry have quale to acknowledge the limitations of authorship attribution, because it necessarily assumes that the correct target author is indeed included in the set of candidates. Sopra many real-world cases, this problematic assumption cannot possibly be made, because the set of relevant candidates is difficult or impossible sicuro establish beforehand. Because of this, the setup of authorship verification has recently been introduced as a new framework: here, the task is esatto verify whether or not an anonymous document was written by one or several of a series of candidate authors. Sopra some sense, authorship verification redefines the text categorization problem by adding an additional category label: ‘None of the above.’
Durante the present context, it should be emphasized that the problem posed by the HA is per ‘vanilla’ example of per problem sopra authorship verification: while the insieme indeed contains per number of (auto-) attributions, the veracity of all of these has been questioned sopra previous scholarship
Verification is hence an increasingly common experimental setup durante authorship studies, and is the topic of a dedicated track sopra the yearly PAN competition, an annual competition on finding computational solutions to issues durante present-day textual forensics, mostly related puro the detection of plagiarism, authorship, and accommodant software misuse (such as grooming or Wikipedia vandalism).27 27 The competition’s website is pan.webis.de. The most recent survey of an authorship verification track is: Anche. Stamatatos et al., ‘Overview of the author identification App meddle task at PAN 2015′ per Working Libretto Papers of the CLEF 2015 Evaluation Labs, anche. L. Cappellato et al. (2015). Generally speaking, authorship verification is per more generic problem than authorship attribution – i.addirittura. every attribution problem could, con principle, be cast as a verification problem – but it has also proven to be more challenging. Mediante our experiments, we have therefore attempted puro radically minimize any assumptions on our part as sicuro the authorial provenance of the texts mediante the HA. For each piece of text analysed below, we propose sicuro independently assess the probability that it was written by one of the (alleged) individual authors identified con the campione.