Literary and Linguistic Computing · 2002 · 596 citations · 0 references
Literary TheoryStylistic AnalysisWriter IdentificationText MiningLiterary CriticismLanguage TestingRelative FrequenciesCorpus AnalysisNew ProcedureLanguage StudiesLanguage-based ApproachLiterary StudyCreative WritingAuthor ProfilingImaginative WritingInterdisciplinary StudiesStylistic DifferenceDistributional SemanticsLiterary HistoryLikely AuthorshipArtsLinguistics
The paper extends prior work that uses relative frequencies of common words to compare texts and attribute authorship, highlighting the growing sophistication and reliability of such methods. It aims to provide a detailed account of the procedure, report results from extensive trials, and evaluate its strengths and limitations. The method compares texts by analyzing the relative frequencies of very common words, applying this approach across a large set of trials to assess performance. The procedure accurately attributes authorship for texts over 1,500 words, proves useful for narrowing candidate authors even for texts as short as 100 words, but performs poorly on genre‑uncharacteristic works or those separated by long time spans.
This paper is a companion to my ‘Questions of authorship: attribution and beyond’, in which I sketched a new way of using the relative frequencies of the very common words for comparing written texts and testing their likely authorship. The main emphasis of that paper was not on the new procedure but on the broader consequences of our increasing sophistication in making such comparisons and the increasing (although never absolute) reliability of our inferences about authorship. My present objects, accordingly, are to give a more complete account of the procedure itself; to report the outcome of an extensive set of trials; and to consider the strengths and limitations of the new procedure. The procedure offers a simple but comparatively accurate addition to our current methods of distinguishing the most likely author of texts exceeding about 1,500 words in length. It is of even greater value as a method of reducing the field of likely candidates for texts of as little as 100 words in length. Not unexpectedly, it works least well with texts of a genre uncharacteristic of their author and, in one case, with texts far separated in time across a long literary career. Its possible use for other classificatory tasks has not yet been investigated.