Browsing Amazon.com the other day, as is my wont, I was reminded of a rather interesting feature they served up a while back: SIPs.

Amazon.com’s Statistically Improbable Phrases, or “SIPs”, are the most distinctive phrases in the text of books in the Search Inside!™ program. To identify SIPs, our computers scan the text of all books in the Search Inside! program. If they find a phrase that occurs a large number of times in a particular book relative to all Search Inside! books, that phrase is a SIP in that book.

SIPs are not necessarily improbable within a particular book, but they are improbable relative to all books in Search Inside!. For example, most SIPs for a book on taxes are tax related. But because we display SIPs in order of their improbability score, the first SIPs will be on tax topics that this book mentions more often than other tax books. For works of fiction, SIPs tend to be distinctive word combinations that often hint at important plot elements.

And so we find that STML favourite The Secret Agent by Joseph Conrad yields such predictable SIPS as “robust anarchist”, “gentlemen lodgers”, “perfect anarchist” and “old terrorist”, while William Burroughs’ Naked Lunch has the more visceral “old gash”, “old junky”, “his cock” and “sick morning”. There’s a good literary guessing game to be had here.

Likewise, Ulysses gives us the wonderful and unmistakeable “ute ute ute”, “tooraloom tooraloom tooraloom”, “base barreltone” (and the somewhat more prosaic “quaker librarian”); and I challenge you to come up with a set of words which could better describe the writings of Iain Sinclair than “retail landfill”, “soft estates”, “payroll boys”, “motorway circuit” and “orbital walk” (from London Orbital). Strange juxtapositions occur too: Walter de la Mare would probably be unimpressed to find himself grouped together with Friction 5: Best Gay Erotic Fiction under the phrase “fat cock” (“The horny old Gardener’s fast asleep; The fat cock Thrush To his nest has gone; And the dew shines bright In the rising Moon”).

For their own reasons, Amazon does not allow you to search for your own SIPs, only giving you access to those they have discovered themselves – this is probably because searching for SIPs actually lets you search all text in the Amazon Search Inside program, which might well lead to some Google Print-type copyright hoohah.

Nevertheless, out of grand generosity, and because noone else appears to have done it, your friends at STML have come up with a solution. Behold: