81–90 of 205 posts
Earlier quoted context omitted.
Discovery engines are pretty easy if you just use clustering unless you allow transitivity (book in two clusters can be used to suggest a book in either cluster)
If it is so easy, why most of them sucks?
My problem with Goodreads isn't the recommendations engine. The recommendations are fine. I'm actually skeptical that any ML recommendation engine is going to recommend better books than my friends will. The only thing I expect from a recommendation engine is discovery , by which I mean finding new things that neither I nor my friends have read that look interesting. Whether they're good is another story altogether..…
After reading and heavily agreeing with this post, I came to the conclusion that either goodreads is not really trying, or -more likely- the data is just not good enough to make decent recommendations. There are so many biases in the review data that are impossible to fix in any kind of sparse matrix recommendation algorithm. For those who want to try anyway, it might be worth downloading an existing dataset (1) (104…
the best way is friending/following people and learning their tastes compared to yours
e: if you go to a specific book and look up similar books, goodreads actually does a pretty good job https://www.goodreads.com/book/similar/1994351-j-r
Earlier quoted context omitted.
> there are very few of us. we are trying This implies support for Goodreads at Amazon is very thin. It could be read as a critical statement (even though it's pretty clear to everyone that the site very clearly stagnated since the acquisition, focusing almost exclusively on Kindle integration). Amazon management is famously militaristic in attitude and would likely take action against a low-level employee criticizin…
> management is famously militaristic Although I know that Amazon is hiring intelligence operatives[0] to bust unions, this aspect (militaristic middle management) is news to me. Where can I learn more? 0. https://www.theverge.com/2020/9/1/21417401/amazon-job-listin...
I'm pretty sure it was also reported in the past that Bezos traditionally favored ex-military for manager positions when Amazon was starting, but I cannot find a source atm (seems like yesterday to me but more than 20 years have since passed...).
Haven't used it myself since it's in beta but I have been keeping my eyes on this for a while: https://beta.readng.co/ , https://twitter.com/readngco
Hi, I'm building this! Thanks for sharing. It's pretty basic right at the moment and we've a lot left to build (largely a reading list only, we've got more in the works) – but here's my profile as a preview, since our marketing site & messaging needs a bit of work: https://beta.readng.co/user/joe
Earlier quoted context omitted.
Can we have half stars or quarter stars? I read a lot of books, and choosing full-star 1 to 5 makes the ratings pretty useless for people who read a lot. My internal rankings are: 1 hated it/was offended/didn't finish 2 disliked it/likely didn't finish 3 finished but it was a struggle 4 finished/enjoyed/had some issues 5 finished fast/really enjoyed/may or may not have still had issues. If I look back at the 30 to 50…
I have been rating a year or so after reading based on how much of the book I remember or how much it influenced me. It's made rating much easier.
Also, if you asked me about a book I read a year ago, I wouldn't be able to do much more than confirm I read it. That's part of why I use Goodreads.
The exact same books/text for about 2 years. Torture...