Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I Want to Fix Goodreads

prepend.com

Post reply on HN
Print view View original

191–200 of 205 posts

Re: I Want to Fix Goodreads

#191

Post by prepend »

Zanni wrote: post #131
onlyrealcuzzo wrote: post #115

Earlier quoted context omitted.

Really? GoodReads reviews have devolved to complete garbage. The first few pages of reviews are always from the same people trying to be GoodReads famous. Everyone gives everything 5-star reviews because they get more likes for positive reviews. The user reviews mean nothing. I'd like to have a way to see what people actually think about books. But on GoodReads that's almost impossible to find. I'm surprised there is…

Interesting point about reviewers skewing positive for popularity. My big issue with most recommendation engines is that they're biased towards false positives rather than false negatives. The other way would lead to fewer, more focused recommendations. In particular, I'd like to see an engine take a reviewer's dislikes into account more. If someone likes (switching to film for an accessible example) Cinderella, The…

I would think that the challenge is to find good recommenders rather than specific recommendations.

If I can find similar tastes, maybe a little bit different, then that will result in good recommendations.

So I would want to find people who both like similar things but also dislike similar things. It will be interesting to find people my similarity and see which are best at finding books I like.

Re: I Want to Fix Goodreads

#192

Post by prepend »

esquire_900 wrote: post #38

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…

Thanks for posting this. I googled around and came up empty.

While I wish companies did more open data posts, I’m glad that researchers are filling the gap, sort of, by making data sets and analyses like yours.

Re: I Want to Fix Goodreads

#193

Post by prepend »

munificent wrote: post #93

> They recommend different versions of books I’ve read. They recommend two different versions of Lord of the Rings (one of my favorite books), but I guess they don’t know these are the same book. This is failure mode of recommendations is so common and so catastrophically useless that I do not understand how it has not been solved. I'm into photography, so every now and then I buy a lens from Amazon. Immediately afte…

I think this is because the ad networks don’t have insight to your purchase data. So they don’t know if you’ve bought and converted or not, but know that people who searched for something are more likely to buy if advertised the dickens out of for the next few weeks.

That’s my theory at least, but even Amazon will show ads for stuff I bought on amazon. Not sure if that’s just them being stupid.

Re: I Want to Fix Goodreads

#194

Post by rexpop »

sillysaurusx wrote: post #92
rexpop wrote: post #55

Earlier quoted context omitted.

> i could be fired for posting. Yikes, that's rather dramatic! Especially since all you've said is "we're working to fix it. changes soon." That's a pretty harmless statement, I would think. What gives you the idea that such statements put your employment at risk?

I downvoted you but I feel bad for not explaining why. One of my memories: Being pulled into a side office and grilled for a half hour for posting a similarly harmless statement to HN. So your comment triggered mild PTSD. It's not your place as an individual employee to post about your employer. You work in a team setting. If the team decides it's appropriate to post to HN, then that's fine. But you alone do not get…

> It's not your place

Strange how your response to abuse isn't to warn us about abuse, but to moralize about the actions through which your abuser justified their emotional violence.

Re: I Want to Fix Goodreads

#195

Post by sam_lynx »

sillysaurusx wrote: post #177
sam_lynx wrote: post #157

Earlier quoted context omitted.

What? You are suggesting that a person is unable to share his personal experiences and opinions unless their employer agrees? Obviously this may damage the company, but personally I have no sympathy for a company worth billions of dollars who is not known for their fair treatment of workers at all. I see nothing immoral in the original commenter releasing this information.

It doesn't matter whether you see something immoral about it. Employers do punish employees for doing so.

Yes, that is why he used a burner account.

Re: I Want to Fix Goodreads

#196

Post by sam_lynx »

SamBam wrote: post #178
sam_lynx wrote: post #159

Earlier quoted context omitted.

Part of what makes YouTube’s recommendation algorithm so powerful is that it doesn’t necessarily have to be very good. I scrolled through my recommendations just now and only found one video after scrolling through fifteen that I was interested in watching — but that’s fine, since it’s easy to decide if you might like a video based on its title, thumbnail, and creator. However, if YouTube was as good at recommending…

How does that follow? I can't imagine that there are any book recommendations -- be they your friends, the Book Review section of your favorite newspaper, or whatever -- that gets things right for almost every single review. That's absurd. When I see a book recommendation, I read the associated review (if it has one), read other people's reviews, look at the author and the blurb, and, yes, even the cover. That tells…

Hm, I change my mind, you are correct.

Re: I Want to Fix Goodreads

#197

Post by zeroonetwothree »

lazyasciiart wrote: post #36
cpsempek wrote: post #26

I'm skeptical of this person's ability to "know" what they don't want to read. E.g., they are recommended Shoe Dog and a King novel, which they claim they don't want to read. However, if other people have read similar books and rated them similarly to this person and have read Shoe Dog and that King novel and rated those well, then this person may like those books. It seems they are assuming they won't like them, but…

Huh, I get recommended Murakami a lot but really didn't enjoy Colorless - maybe I'll try a different one.

Colorless is one of his worst books IMO. I would recommend Hard-Boiled Wonderland and the End of the World or Kafka on the Shore.

Re: I Want to Fix Goodreads

#198

Post by Jemaclus »

onlyrealcuzzo wrote: post #115
Jemaclus wrote: post #10

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..…

Really? GoodReads reviews have devolved to complete garbage. The first few pages of reviews are always from the same people trying to be GoodReads famous. Everyone gives everything 5-star reviews because they get more likes for positive reviews. The user reviews mean nothing. I'd like to have a way to see what people actually think about books. But on GoodReads that's almost impossible to find. I'm surprised there is…

I think they're fine? I didn't say great. In fact, I did say that I don't think ML will ever live up to my friends' recommendations, and that's primarily what I look at on Goodreads. My news feed thing is a list of books my friends want to read, are reading, or have read and rated, and that's more than good enough for me.

As far as the recommendations goes, I mean, I guess you could say I skip past most of them and only get the interesting ones, but at least the algorithm put it in front of me.

Again, my bigger problem with Goodreads is the performance. I'd use it a lot more and interact with my friends a lot more (and thus get better recs from them!) if it was a speedier site.

Re: I Want to Fix Goodreads

#199

Post by Jemaclus »

prepend wrote: post #191
Zanni wrote: post #131

Earlier quoted context omitted.

Interesting point about reviewers skewing positive for popularity. My big issue with most recommendation engines is that they're biased towards false positives rather than false negatives. The other way would lead to fewer, more focused recommendations. In particular, I'd like to see an engine take a reviewer's dislikes into account more. If someone likes (switching to film for an accessible example) Cinderella, The…

I would think that the challenge is to find good recommenders rather than specific recommendations. If I can find similar tastes, maybe a little bit different, then that will result in good recommendations. So I would want to find people who both like similar things but also dislike similar things. It will be interesting to find people my similarity and see which are best at finding books I like.

I follow my friends, and my friends tend to have good taste! This is essentially my strategy. I do have a few friends who have recommended books that I didn't like, so I just don't listen to their recs anymore. Solved problem!

That's one of the problems I have with ML-based recommenders. I can't identify any particular ML algorithm, and therefore I can't say "This one has consistently given me bad recommendations, so I'll ignore it. But I do like this one over here." Whereas with my friends, I know that Lori and Nicole gives good recs and Brad doesn't, so I'll ignore Brad's and read recs from the other two.

Re: I Want to Fix Goodreads

#200

Post by jordiburgos »

johnfn wrote: post #21

Good lord what I wouldn’t give for a better goodreads. Never has so much useful and actionable data been squandered. For example, I could write pages about how bad the “top books” lists are. The Goodreads Choice Awards are purely and literally popularity contests, for example. Why would this be the case - you have millions of user ratings, you should be using those to surface exciting and unknown books rather than th…

Please share the results of your script !! :)
Post reply on HN