The present invention is directed to a method for determining a document's
overall effectiveness or quality using a technique that employs detecting
correlation between document citation rate and document presentation
elements such as style and layout. A document's citation rate is the
number of citations of or references to that document from other
documents. This is taken as an indicator of a document's overall
effectiveness. This invention employs automated means to obtain, for a
sample of documents, both presentation data and citation rate data.
Presentation data is obtained, for each document in the sample, by
automated inspection of the document, for stylistic elements. The
citation rate for each document is based on the number of citations
(e.g., hyperlinks) to that document from another set of documents, the
larger the set the better. The present invention then computes the
statistical correlation of document citation rate versus presentation
elements used, in a straightforward manner to identify correlation
between the citation rate and presentation element(s).