Key points are not available for this paper at this time.
Abstract Even in its very early stages, Alzheimer's disease leads to changes in language that can be detected by computational analysis. These changes may include a reduced, vaguer, and more abstract vocabulary, and reduced syntactic complexity. But do these changes affect an author's essential style? We experiment with a number of standard features for authorship attribution and authorship verification to see whether they recognize late works written by authors known to have had Alzheimer's disease as being by the same author as their earlier works. The authors whom we study are Iris Murdoch and Agatha Christie. Our control author (without Alzheimer's) is P. D. James. Our results were equivocal, as different frameworks yielded contrary results, but an SVM classifier was able to make age discriminations, or nearly so, for all three authors, thereby casting doubt on the underlying axiom that an author's essential style is invariant in the absence of cognitive decline. Acknowledgements This work was supported financially by the Natural Sciences and Engineering Research Council of Canada. We are grateful to Michelle Tran for conducting a pilot study of unmasking on these data. Notes 1Nicholas et al.; Maxim and Bryan. 2Maxim and Bryan. 3Comparisons of these measures across individuals are not meaningful; what matters is change within the individual. 4Le et al. 5Garrard et al. 6Lancashire, 210–11. 7Conradi, 19, 654. 8Love; Juola; Lancashire. 9Juola; Grieve; Koppel, Schler, and Argamon; Stamatatos. 10Maxim and Bryan. 11We are speaking here, of course, of the earlier stages of Alzheimer's, in which the patient is still able to write, albeit perhaps poorly, as Murdoch and Christie did. In the later stages of the disease, when linguistic abilities may break down completely, the question becomes meaningless. 12Said, 6. 13Ian Lancashire (218) points to Anne M. Wyatt-Brown's characterization of the late style of Barbara Pym, which reflects both a new world view and its surface realization: "Most reviewers and friends commented upon the uncharacteristic undercurrents of depression and melancholy. … Furthermore, she herself described her desire to pare down her writing, to make things spare" (Wyatt-Brown, 837). But it remains an open question as to whether Pym's new spareness or conciseness ("Pym had concentrated so passionately on making her point that later she had to add 12,000 words to make her manuscript publishable" ibid.) resulted in any marked change in the stylometrics of her writing. 14Koppel, Schler, and Bonchek-Dokow; Koppel, Schler, and Argamon. 15Koppel and Schler; see also Koppel, Schler, and Bonchek-Dokow; Koppel, Schler, and Argamon. 16See also Kestemont et al. (this issue). 17Koppel, Schler, and Bonchek-Dokow; Koppel, Schler, and Argamon. 18Chang and Lin. 19Hall et al. 20Grieve. 21Juola; Hirst and Feiguina. 22R Development Core Team. 23See Lancashire for an example of research aimed at developing this understanding.
Hirst et al. (Tue,) studied this question.