Key points are not available for this paper at this time.
The thirty most common word-types in many English texts make up about two-fifths of all the word-tokens used in them. The respective frequencies of the word-types can be arrayed hierarchically to form a frequency profile for each text. When a number of profiles are correlated with each other, the resulting matrix shows appropriate resemblances and differences across the range of texts. The whole pattern of interrelationships can then be ‘mapped’, by applying eigen analysis to the correlation-matrix. This form of analysis can be applied to comparisons of dialogue with narrative; of the idiolects of different characters; or — in the territory to which the present paper is addressed — of narrative with narrative. When several narratives are compared, authorial and chronological determinants predominate. When the segments of a single narrative are compared, even subtler stylistic determinants declare themselves and point towards the possibility of a computerassisted literary criticism.
J. F. Burrows (1987) studied this question.