[ad_1]
Amazon’s Statistically Improbable Phrases (SIP) is a search technology that identifies unique or frequently occurring phrases in books using the Search Inside!® program. It allows users to search for specific books using quotes or phrases and can also be used for web content searches. While not perfect, it can reduce search times.
Statistically Improbable Phrases, or SIP, is a search technology developed by Amazon.com to search the content of books for phrases they contain that might be unique or occur often. This is part of Amazon’s patented Search Inside!® technology program. Essentially, Search Inside® gives Amazon access to the full or partial text of a book, so that certain phrases can be used to identify that book if statistically improbable phrases are used in a search.
The name of this technology is a bit confusing. When you search, you want what you’re looking for to match closely. By identifying a unique phrase in a book, if you use that phrase to search it’s unlikely your search will list anything you don’t want. If you’re looking for a specific book and don’t remember the title but do remember a quote from it, you can use the quote to search for the book.
Alternatively, you may want to search for a specific topic, within a larger topic. For example, if you wanted to look up a book with career advice, but what you really wanted to read about was how to network for jobs, you could search for “networking” instead of “career advice.” Instantly, some of the most relevant searches show up on Amazon’s search results page, including books like Dig Close Before You’re Thirsty: The Only Network Book You’ll Ever Need.
If you’ve searched with these types of statistically unlikely phrases, you may find that you can get results that aren’t exactly a good match. For example, the top search result for networking is not for professional networking, but information about computer networking and technology. You can improve statistically unlikely sentences by being more specific. For example, you get better results by searching career networking or job networking.
Phrases that are statistically unlikely are actually probable phrases, as a unique phrase for a Search Inside!® book is likely to head the list of things you search for. For example, you could enter a line by Shakespeare from a Shakespeare sonnet to recall books about Shakespeare. This doesn’t always work well as some well-known quotes are used in many other books as titles. You will not find Hamlet if you search “To be or not to be”. Nor will you find Macbeth with statistically improbable sentences like “Get out! Damn place.” Indeed, under the latter term, the first book you will find is the one on stain removal.
Using statistically unlikely phrases is also a way to search for web content, and web crawlers can use similar technology so people can more effectively and specifically search for certain unique lines. It’s not a perfect technology since a web crawler doesn’t necessarily evaluate the content. It can search for keyword repetition which allows people to find pieces with the most keyword repetitions. Not all books on Amazon have Search Inside!® technology, but this seems to be the trend. Ultimately, even if the system is slightly flawed, it could reduce search times.
[ad_2]