Where's the Pandora for e-book recommendations?

[Bob Russell]

For new book readers, one of the trickiest aspects of book reading can be deciding what to read. Especially if you like fiction. Everyone seems to have a different idea of what's a great book, so recommendations often don't work at all. Many of my favorite books are not the best, they're just fun to read. Maybe even formula-based books, but with a formula that works for me. For example, I don't miss a single new release of Vince Flynn or Brad Thor. But other similar popular writers aren't worth my time because they just aren't fun for me to read.

Even worse, you can't tell if you are going to like a book by the first page, first paragraph, first chapter or whatever. I know that many people think you can tell, but I don't believe it. I really don't enjoy the first pages of Dickens books, but once I've invested enough into the book to get a feel for the main characters I'm absolutely hooked. Other books are really fun for the first chapter or so, like Pride and Prejudice, and then I can't make myself finish the book because it just goes on and on when I wish it would get to something interesting again. When it never seems to become fun again, I put it aside, frustrated about the time I wasted being bored. Or maybe I get lost in the details and it gets to be too much work to follow along. At any rate, there doesn't seem to be any great way to tell if I'm going to like a book or not, even with the recommendations of other honest and helpful readers.

But if you combine various recommendations that tell you what readers liked and disliked about the book and what other types of books they like, read a couple of reviews and book descriptions, and read a sample chapter or two, the odds of picking a good book really go up. You get a little bit of detail that helps you decide if the real characteristics of the book are what you like, or what turn you off.

That reminds me a whole lot of a personalized music streaming service called Pandora. They aim to play just the music you like, while keeping some variety and helping you to discover new artists along the way. If you like music, I'd highly recommend it.

What's most interesting is that they use an analysis of the relevant characteristics of music to match you to the music you like.

Since we started back in 2000, we have been hard at work on the Music Genome Project. It's the most comprehensive analysis of music ever undertaken. Together our team of fifty musician-analysts has been listening to music, one song at a time, studying and collecting literally hundreds of musical details on every song. It takes 20-30 minutes per song to capture all of the little details that give each recording its magical sound - melody, harmony, instrumentation, rhythm, vocals, lyrics ... and more - close to 400 attributes! We continue this work every day to keep up with the incredible flow of great new music coming from studios, stadiums and garages around the country

My thought for today is that something similar should work great for books as well. Study what makes books worth reading and fun or valuable. Ask people what books they like and don't like, and why. Provide a catalog of book qualities and use it to provide a personalized stream of book recommendations that can be evolved with your additional input about books you've read. In other words, do something a little deeper than Netflix or the standard social book recommendation sites. It's all the more important for books than songs - you can waste a lot more time and effort on a bad book than a bad song.

We need a better way to get book recommendations. Sure, Pandora messes up sometimes as well. But even when they recommend something I don't like, at least I can see why they recommended it, and start to learn for myself what I don't like. It's a recommendation method that gets into the details that matter, and shares the "thinking" with me. In my opinion, that's just what we need in the e-book world.

Note: In the comments, Erik (aka eaderigt) has supplied a link to the BookLamp service, which seems to be very much along these lines. They are just trying to get off the ground, but it seems promising..

[pilotbob]

How about http://www.whatshouldireadnext.com.

It's not as scientific as the music gnome project... but it offers some good suggestions.

BOb

[Gideon]

I've found that http://www.whatshouldireadnext.com. fails thoroughly and completely every time I've used it.

I've often wondered where such a service is as well. There are such things, of course, but I've found they're all pretty terrible. Amazon does a better job suggesting books to me than they often do.

[AnemicOak]

Originally Posted by pilotbob

How about http://www.whatshouldireadnext.com.

It's not as scientific as the music gnome project... but it offers some good suggestions.

BOb

I've had better luck using Fantasic Fiction's 'Visitors to this page also looked at these authors' section on an author's given page.

[AMacD]

Some books are so poorly written that it takes less than a paragraph to reject that one. Authors that don't know the difference amongst "there, they're and their" for example. To is not equal to two or too. Or foul language just for shock effect that doesn't lend to the tone of the story. It should not take a quarter of a book to establish a love of the characters. I finish most books that I have started and managed to get through the first quarter without losing interest or getting so confused that I am totally lost. On the other hand I am not going to waste my time on a hopeless book when there are a thousand more in the queue waiting to be enjoyed.

[slayda]

This is an interesting concept only apparently my likes are too wierd since almost every book friends recommend turns out to be something I don't like. I could probably use there recommendations as a negative and be ahead of the game.

I do understand about there, they're and their" for example & to is not equal to two or too. but "your & you're" bothers me more and I hate to read "alot" as in a lot of books. Before I retired, a coworker swore that was the correct spelling. He looked it up on Wikipedia and read, " 'Alot' - how a moron spells 'a lot'." I felt quite vendicated.

[Elsi]

Originally Posted by AMacD

Some books are so poorly written that it takes less than a paragraph to reject that one. ... I am not going to waste my time on a hopeless book when there are a thousand more in the queue waiting to be enjoyed.

One book that I thoroughly enjoyed last year was Snow Ball by April L Hamilton. I bought a Kindle edition at Amazon after April posted something about the book here at MobileRead. When I looked at the book description on Amazon.com it sounded fairly good, and there were even a couple of reviews indicating that the reviewer enjoyed the book, so I bought it. While the story is good and the dialog is superb, there are flaws in the book. This is the first paragraph:

Velma and Naomi sat in their usual spot, the back left-hand booth at the IHOP in Sheboygan, Wisconsin. Naomi, the Canadian, was a native of Winnipeg, and the American, Velma, lived in Sheboygan Falls. Naomi was the taller of the two at 5' 7". Her long, dark brown hair was pulled back in a ponytail and secured with a white, fake fur scrunchie designed to match the fake fur trim on her sweater. Her blue eyes had a slightly bugged appearance but she had creamy white, freckled skin and very high cheekbones and so was still a fairly attractive woman. Velma stood about 5' 4" and had a tendency toward plumpness. She wore her shoulder-length, medium blonde hair cinched up in a clip. She too had enviable skin, though her almost black eyes were certainly the lovelier between the two of them. Both spoke with the nasal, vaguely Scandinavian-sounding twang and singsong cadence so common to the region. Naomi's husband Peter and Velma's husband Walt ran a business together with some other associates on both sides of the border. Peter acted as the Canadian point of contact and Walt was his counterpart in the U.S. for their particular part of the operation. Velma and Naomi met twice a month in this same restaurant to exchange pictures of their kids, to plan joint family vacations and to carry packages to one another's husbands.

I took the time to write to April and comment that her introduction needed some work to hook the reader right off the bat because the rest of the book is so good and as I said, the dialogue is superb. She replied that she was attempting to portray the two protagonists are "just ordinary women with ordinary lives". And I agree that would be a good objective, but she missed the boat with this lack-luster approach. I think that she could have met her goal without a stiff/stilted intro. Unfortunately, if someone downloads a sample, they may give up before getting to the good stuff and miss out on a zany, madcap adventure.

[ectoplasm]

Originally Posted by slayda

... I could probably use there recommendations as a negative and be ahead of the game.

I do understand about there, they're and their" for example & to is not equal to two or too. but ...

Sorry, this is too ironic to pass up ;-)

[DonRobodroid]

Pointing out that

It takes 20-30 hours per book to capture all of the little details that give each writing its magical reading experience

I second Bob's thought!

Cheers,
- Don [:-]

[Elsi]

Originally Posted by Bob Russell

My thought for today is that something similar should work great for books as well. Study what makes books worth reading and fun or valuable. Ask people what books they like and don't like, and why. Provide a catalog of book qualities and use it to provide a personalized stream of book recommendations that can be evolved with your additional input about books you've read. In other words, do something a little deeper than Netflix or the standard social book recommendation sites. It's all the more important for books than songs - you can waste a lot more time and effort on a bad book than a bad song.

We need a better way to get book recommendations. Sure, Pandora messes up sometimes as well. But even when they recommend something I don't like, at least I can see why they recommended it, and start to learn for myself what I don't like. It's a recommendation method that gets into the details that matter, and shares the "thinking" with me. In my opinion, that's just what we need in the e-book world.

Amazon's recommendations seem to be pretty good. They offer you the opportunity to refine their recommendations, too. But, their system seems to be overly influenced by recent purchases. So, as I've availed myself of almost every Kindle freebie that has come by, the book recommendations have become more skewed to those types of books. Same thing happened when my husband didn't notice that the computer was logged into my Amazon account and he ordered an album by Kylie Minogue. Took me *months* to convince Amazon that I didn't want any more of her music!

It would be nice if Goodreads or LibraryThing had as smart of a recommendations system as Amazon. (Yeah, OK. I understand that this personalization of the shopping system is one area where Amazon has it all over their competition.) Since the books I list at these sites are those I have actually *read* or those I plan to read fairly soon, the recommendations wouldn't be unduly influenced by books that I downloaded, but haven't gotten around to reading.

[Dopedangel]

Have you tried
http://www.gnooks.com/

"Gnooks is a self-adapting community system based on the gnod engine. Discover new writers you will like, travel the map. of literature and discuss your favorite books and authors. "


"Gnod is an experiment in the field of artificial intelligence. Its a self-adapting system, living on this server and 'talking' to everyone who comes along. Gnods intention is to learn about the outer world and to learn 'understanding' its visitors. This enables gnod to share all its wisdom with you in an intuitive and efficient way. You might call it a search-engine to find things you don't know about."

[Manpreet]

Well I haven't read any negative review of any book I came across on Amazon, so I always prefer other sites with user reviews about the books and I befriend a lot of book readers. so usually I get something good to read from their suggestion.

But I do think that sometimes some recommendations just disappoints you much.
Like was with Rachel Morgan series. A good friend of mine suggested me the series and pressed me much to read it. I read the first two books and felt too much disappointed. May be that was because I had already read Dresden Files Series and he thought I might like Rachel Morgan too but the fact was otherwise.
So now I too sometimes wonder that the suggestion of some friend might be a waste of time.

[pilotbob]

Originally Posted by Elsi

Same thing happened when my husband didn't notice that the computer was logged into my Amazon account and he ordered an album by Kylie Minogue. Took me *months* to convince Amazon that I didn't want any more of her music!

I think you can just go and specify that a purchase was a gift and it will stop considering it in the recommendation system.

BOb

[13xforever]

Have anyone tried BookLamp.org? The only problem there is that it's been in beta for ages.

[Krystian Galaj]

On a related note, where's Pandora for non-US listeners? The only thing I can see on the site is a notice that I can't use the service as I'm in the wrong country...