BookLamp is a project that the people at Amazon.com would be idiots to pass up buying.
It's a machine learning tool that's been designed to go through books and analyze not only how they're written, but also help group together novels that share similar structures and styles. The hope is to help people discover books they may like based on previously read novels, or what kind of reading experience they're going for. Internet radio recommendation service Pandora does something similar, employing a thumbs up and down system combined with listening history.
Because BookLamp's system uses machine learning, it skips the three major aspects of each book that humans usually tally: story line and plot, the characters, and writing style. Instead, it figures out bits of these three items by using written cues and quantifiers like word density, pacing, action, character dialogue (as noted by quotations), and level of description. The system also blends in one to five star ratings from Amazon.com.
(click to enlarge) BookLamp's stats analysis looks at a book and figure out how it's written based on five factors.
(Credit: CNET Networks)So far, the database has 179 books, but is tracking more than 700,000 data points over 30,000 scenes from those titles. If it were to scale to track more works, in theory the results for related items would be even more precise. In its current state, users can go in and pick from one of the titles and get recommendations for similar titles, or view the graphs of what the system has recorded for its pacing, density, and other characteristics.
One of the coolest features, and the one I think is the killer app is the pacing analysis. It will go through and figure out when the pace of a book speeds up or slows down.
In the video demo (embedded after the break), creator Aaron Stanton picks Michael Crichton's Jurassic Park as an example, and demonstrates that BookLamp was smart enough to detect when the pace ramps up, including on what page that change occurs. I could see this being a great way to check and see if you're wasting your time on a read that's off to an incredibly slow start and potentially going nowhere. Instead of giving up, you could simply give the chart a quick look.
The project has been around since 2003 and continues to build up its database. There's a sign-up form to request a work to be added. You can also play around with the browsing and stats tool by registering. Be sure to hit the read more button to check out the video walk-through.
[via Digg]
... Read more
Far separate from RSS readers lays the land of news aggregators. One of the more well-known ones is Google News, but there are also social solutions like Newsvine that let the community decide what news items rise to the top based on what's coming over the wire. A new service named Tiinker (that's somewhere in the middle) opened its doors earlier this week. The site's been in private beta since late last year, and can most easily be described as a mix between Google News and StumbleUpon. It's not meant to replace a standard news page by any means, but instead is designed to let you whittle down what types of stories you like in order to get future recommendations that are similar. The ones you mark as not liking, Tiinker will simply get rid of.
Everything on the site is handled with three basic controls, a thumbs up and down button, and a way to bookmark content that goes into a separate feed that you can share with others. The service will also keep track of which stories you've marked as liking, so you can go back and read them later. In order to abate users limiting themselves to just a few types of content, there's also a "lucky" dip section, which chooses a story that's outside of your taste.
The ultimate goal of this and services like Spotback are to help you get a news feed that's been hand-tailored to your preferences so that the only stories you'll see are ones you're interested in. Of course what makes that part critical is the source list, which is where Tiinker's a little short-sighted. There are many good sources that articles seem to pop up from, but there's no way to go in and "tinker" the complete list to see what's on it or add new, independent sources. This is mostly because of the machine learning system that's set up to balance the tastes of the entire user base, but it's a bummer when you're in the dark about where the content is coming from. Interestingly enough, up until last month the service had a built-in RSS reader that let you do such a thing, but it was pulled down for retooling.
I like the idea of Tiinker, although it's not useful to me for news or content suggestions as I'm an RSS enthusiast who reads a lot of social news sites. It's definitely a handy way to get a smattering of new feeds and story suggestions, and the machine learning concept shows promise, but until they give a little more control over where the content is coming from, advanced users will likely want to stick to a social news service or feed aggregator like Feed Each Other, and still private Streamy to get interesting news links from humans.
Tiinker pulls in news from a variety of sources. Pick the ones you like, and it will do its best to find you more that are similar.
(Credit: CNET Networks)
- prev
- 1
- next
