# Amazon's book recommendation engine is dumb -- any better ones? **URL:** \ **Category:** Cafe Society\ **Created:** [May 19, 2009, 7:02pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998 "2009-05-19T19:02:45Z")\ **Posts on this page:** 9\ **Page:** 3
**Author:** ![Justin\_Bailey](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/justin_bailey/32/8792_2.png) [@Justin\_Bailey](https://boards.straightdope.com/u/Justin_Bailey)\ **Post date:** [May 23, 2009, 2:54pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/41 "2009-05-23T14:54:52Z")
As a librarian, some of these suggestions look very useful and I’m going to share them with the rest of the Reference Desk staff. But if your library has access to EBSCO’s NoveList database, it is the greatest book recommendation engine hands down. Due to budget cuts, my library system recently had to get rid of it, but ThisOneNext and Literature Map at least give me a starting point for something similar. ---
**Author:** ![wonderlust](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/wonderlust/32/7237_2.png) [@wonderlust](https://boards.straightdope.com/u/wonderlust)\ **Post date:** [May 23, 2009, 4:24pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/42 "2009-05-23T16:24:12Z")
I just typed Stephen King into the Literature Map; they placed J.R.R. Tolkein right next to him, and out on the side Clive Barker is right next to Jane Austin! 😃 ---
**Author:** ![Khadaji](https://avatars.discourse-cdn.com/v4/letter/k/9e8a1a/32.png) [@Khadaji](https://boards.straightdope.com/u/Khadaji)\ **Post date:** [May 23, 2009, 5:01pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/43 "2009-05-23T17:01:09Z")
> [@wonderlust](#): > > I just typed Stephen King into the Literature Map; they placed J.R.R. Tolkein right next to him, and out on the side Clive Barker is right next to Jane Austin! 😃 Wow - and Ayn Rand and John Steinbeck? I’m struggling a little with some of these. ---
**Author:** ![Chronos](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/chronos/32/134_2.png) [@Chronos](https://boards.straightdope.com/u/Chronos)\ **Post date:** [May 23, 2009, 6:08pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/44 "2009-05-23T18:08:13Z")
> [@](#): > > I have to admit, I use Amazon recommendations in a way they probably didn’t intend. I think this is a case of “a rising tide lifts all ships”… Yeah, Amazon would prefer that you buy books from them, but anything that gets people reading more is good for Amazon in the long run. Maybe you won’t be able to find a copy elsewhere, so you’ll buy it anyway. Or maybe you’ll read the book from the library, and recommend it to a friend, who then buys it. Or maybe you’ll just come to like Amazon in general for helping you out with book recommendations, like Macy’s in _Miracle on 34th Street_. And after all, Amazon has listings for books they don’t actually have in stock: Surely, they don’t expect to sell you copies of those books. ---
**Author:** ![AuntiePam](https://avatars.discourse-cdn.com/v4/letter/a/f19dbf/32.png) [@AuntiePam](https://boards.straightdope.com/u/AuntiePam)\ **Post date:** [May 23, 2009, 6:19pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/45 "2009-05-23T18:19:57Z")
Well, this thread has helped me figure out what to do on a rainy Saturday – rate 1128 Amazon transactions! We’ll see if that helps. More likely it’ll result in more buying. I need to see if some of these authors have written anything new. And I need to find a copy of _Slaves of Solitude_ – I ordered it months ago from Amazon but they were unable to deliver. Maybe I can find it used. I rely on the reading threads here for recommendations. After awhile, I know that if X likes a book, I will too. ---
**Author:** ![Waenara](https://avatars.discourse-cdn.com/v4/letter/w/50afbb/32.png) [@Waenara](https://boards.straightdope.com/u/Waenara)\ **Post date:** [May 24, 2009, 6:56am UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/46 "2009-05-24T06:56:18Z")
> [@ultrafilter](#): > > You’re thinking of the [Netflix Prize](http://www.netflixprize.com/). Technically they’re trying to solve a slightly different problem (estimating a user’s ratings of a movie rather than trying to compute a list of recommendations), but you’re basically right. I like the website [movielens](http://movielens.umn.edu/login) - it’s hosted by a research group the University of Minnesota. It doesn’t just give you recommendations, it guesses how you would rate the movie. You enter ratings for movies you have seen (from 0 to 5 stars in 0.5 star increments), and it suggests how you might rate other movies, based on ratings from other people in their database who have similar tastes in movies. I find that the ratings they guess for me are usually very close to the rating I give a movie after I have seen it. [From their FAQ](http://movielens.umn.edu/html/tour/index.html) > [@](#): > > MovieLens uses a technology called collaborative filtering to generate movie recommendations. It works by matching together users with similar opinions about movies. Each member of the system has a ‘neighborhood’ of other like-minded users. Ratings from these neighbors are used to create personalized recommendations for the target user. ---
**Author:** ![fizixgeek](https://avatars.discourse-cdn.com/v4/letter/f/71c47a/32.png) [@fizixgeek](https://boards.straightdope.com/u/fizixgeek)\ **Post date:** [February 2, 2012, 11:23pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/47 "2012-02-02T23:23:18Z")
Try out [bookwonk.org](http://www.bookwonk.org). It uses optical character recognition to actually read books and analyze the language. Then it recommends books that are linguistically similar to your favorites. -FG ---
**Author:** ![dozen](https://avatars.discourse-cdn.com/v4/letter/d/a8b319/32.png) [@dozen](https://boards.straightdope.com/u/dozen)\ **Post date:** [June 9, 2012, 6:03pm UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/48 "2012-06-09T18:03:29Z")
Please check [dozen.softover.com](http://dozen.softover.com) - our attempt to make something that works 🙂 ---
**Author:** ![jabiru](https://avatars.discourse-cdn.com/v4/letter/j/bbce88/32.png) [@jabiru](https://boards.straightdope.com/u/jabiru)\ **Post date:** [June 10, 2012, 12:08am UTC](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998/49 "2012-06-10T00:08:30Z")
> [@fiddlesticks](#): > > Of course, you can tell Amazon that “I already own this book” and “I’m not interested in this book” via various links on those pages. While I don’t think it improves things, at least you won’t see books you have/aren’t interested in any longer. I’ve told Amazon countless times that I already own _Mansfield Park_. It doesn’t bother me overmuch that they keep wanting me to buy _Emma_, which I also own but that they keep recommending me other editions of _Mansfield Park_. I enjoyed it once and read it a second time. I doubt I’ll be reading it again because I have way too many books on my To Read list but if I do decide to read it again, I’ll re-read the copy I already own, not buy another one with all the same words but possibly a different cover. [Previous page](https://boards.straightdope.com/t/amazons-book-recommendation-engine-is-dumb-any-better-ones/496998.md?page=2)