Friday, April 08, 2005

Amazon.com started a weird new feature a few weeks ago--Statistically Improbable Phrases. Here is the reasoning behind them:

Amazon.com's Statistically Improbable Phrases, or "SIPs", show you the interesting, distinctive, or unlikely phrases that occur in the text of books in Search Inside the Book. 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 how many times it occurs across all Search Inside books, that phrase is a SIP in that book.


Now, I'm all for statistically improbable phrases--I love when unexpected combinations of words show up in poems and stories; it's one of my favorite things, actually--but I can't understand the need for this feature. And some of the SIPs they chose are just plain goofy. I thought at first they only did this in non-fiction books ("mystery fruit" shows up as a SIP in Fruitflesh), but now they're popping up in novels, too. The SIPs for The Book of Dead Birds are "bird hospital" and "bridge ladies."

Here are some random SIPs (well, random among friends' books):

--Barbara Kingsolver's Prodigal Summer: "calico skirt", "hemlock grove"
--Ayun Halliday's The Big Rumpus: "salad bin", "dip head", "birthing center", "glitter glue"
--Donna Gershten's Kissing the Virgin's Mouth: "golden zone"
--Caroline Leavitt's Coming Back to Me: "bolted awake"

Someone should write a poem entirely composed of Amazon SIPs!

Update: Fruitflesh has two new SIPs today--"own fruitflesh" and "in your skin." So weird that this is what they've found (I like how the two phrases sound together--"own fruitflesh in your skin." That's what the book's all about, isn't it?!)

No comments: