12-15-2009, 12:31 PM | #1 |
The Dank Side of the Moon
Posts: 35,872
Karma: 118716293
Join Date: Sep 2009
Location: Denver, CO
Device: Kindle2; Kindle Fire
|
Literary Pattern Matching
interesting commentary on software pattern matching and literature.
http://links.techwebnewsletters.com/...TkS1&mt=1&rt=0 exerpt: Pattern matching is one thing computers do really well. Take a bushel of data, throw it at a computer, and be amazed by the results. That's more or less what Sebastian Bernhardsson, Luis Enrique Correa da Rocha, and Petter Minnhagen, all members of Sweden's Umea University Department of Physics, did anyway. What is particularly interesting about their data was that it was a collection of books by Thomas Hardy, D.H. Lawrence, and Herman Melville — authors I haven't thought much about since university. And what the researchers discovered was that by applying statistical analysis and pattern matching techniques to literature written by these authors, they were able to identify unique literary "fingerprints" of each author...... See link above for full text. |
12-15-2009, 02:25 PM | #2 |
Addict
Posts: 236
Karma: 4066
Join Date: Feb 2009
Location: California
Device: Kindle 1 and DX, iPhone
|
This is very cool. I think Google Books and Amazon are both well positioned to build a Pandora for ebooks (previous discussion here: https://www.mobileread.com/forums/showthread.php?t=55891) as they have all the texts as well as the software expertise to compute book fingerprints like this. I don't know if they will, given all the distractions they have to deal with. Perhaps a smaller company can get started with the Gutenberg catalog to build a recommendation system based on fingerprints, and then get acquired by Google or Amazon
|
Advert | |
|
12-15-2009, 03:47 PM | #3 | |
Wizard
Posts: 1,479
Karma: 3846231
Join Date: Apr 2009
Location: Edinburgh, Scotland
Device: Kindle 3, Samsung Galaxy
|
Quote:
Admittedly, the hardware and software are much more powerful now, and so no doubt does a better job of it. But it's hardly new technology. |
|
12-15-2009, 03:54 PM | #4 |
The Dank Side of the Moon
Posts: 35,872
Karma: 118716293
Join Date: Sep 2009
Location: Denver, CO
Device: Kindle2; Kindle Fire
|
I believe that the concept has been around likely even before computers. It's really about the "feel" of a writer's work I think. I'm also quite sure not only the computer technology but the linguistic analysis techniques have improved tremendously since the first attempt.
|
12-16-2009, 02:38 PM | #5 | |
Wizard
Posts: 1,479
Karma: 3846231
Join Date: Apr 2009
Location: Edinburgh, Scotland
Device: Kindle 3, Samsung Galaxy
|
Quote:
|
|
Advert | |
|
12-16-2009, 03:12 PM | #6 |
The Dank Side of the Moon
Posts: 35,872
Karma: 118716293
Join Date: Sep 2009
Location: Denver, CO
Device: Kindle2; Kindle Fire
|
Well, you know how it is with magazines, news, marketing, and fashion everything old is new again.
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
header removal fails, even though test identifies the pattern | hpep | Calibre | 2 | 08-09-2010 12:40 PM |
Better matching/scanning | lbutlr | Calibre | 3 | 08-04-2010 03:44 PM |
Matching Light for Kobo | dixieknits | Kobo Reader | 2 | 07-19-2010 02:50 AM |
Covers and thumbnails not matching in Mobipocket Reader | jlmwrite | Kindle Formats | 3 | 02-22-2010 03:09 AM |
How do I specify TOC pattern? | PaulChernoch | Calibre | 5 | 10-10-2009 01:18 AM |