Finding keywords amongst noise: Automatic text classification without parsing

The amount of text stored on the Internet, and in our libraries, continues to expand at an exponential rate. There is a great practical need to locate relevant content. This requires quick automated methods for classifying textual information, according to subject. We propose a quick statistical approach, which can distinguish between 'keywords' and 'noisewords", like 'the' and 'a', without the need to parse the text into its parts of speech. Our classification is based on an F-statistic, which compares the observed Word Recurrence Interval (WRI) with a simple null hypothesis. We also propose a model to account for the observed distribution of WRI statistics and we subject this model to a number of tests.