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

The Facebook Algorithm Mom Problem

boffosocko.com

Post reply on HN
Print view View original

161–170 of 317 posts

Re: The Facebook Algorithm Mom Problem

#161

Post by Siecje »

ryanbrunner wrote: post #95

I find a lot of sites feel like they're overtuning their recommendation engines, to the detriment of using the site. YouTube is particularly bad for this - given the years of history and somewhat regular viewing of the site, I feel like it should have a relatively good idea of what I'm interested in. Instead, the YouTube homepage seems myopically focused on the last 5-10 videos I watched.

Why are so many videos I have already seen? I guess people re-watch them, or show other people "Hey have you seen this".

But for me it is just silly.

Re: The Facebook Algorithm Mom Problem

#162

Post by njarboe »

differonzi wrote: post #158
jon_richards wrote: post #149

Earlier quoted context omitted.

I've heard the argument that this prevents buyer's remorse. Not sure if it has any merit.

What are the (general) financial consequences of buyer's remorse?

For Amazon with a generous return policy, when a person has buyer's remorse, they can return the item. Lost sale.

Re: The Facebook Algorithm Mom Problem

#163

Post by marksc »

icebraining wrote: post #150
rhizome wrote: post #107

Earlier quoted context omitted.

YouTube would rather you fall into a trance of continuing your recent viewing habits rather than providing a personalized library. It just makes better business sense.

Why does it make better business sense?

It probably massively increases average time on site and average videos viewed, and thus ad revenue.

Re: The Facebook Algorithm Mom Problem

#164

Post by DeltaWhy »

Kubuxu wrote: post #98
frenchie4111 wrote: post #49

Earlier quoted context omitted.

Someone should make a browser extension that will automatically (or provides a button to quickly) load the cached version when a site is down Edit: I just made a super simple bookmarklet that does it: http://mikelyons.org/2017/06/12/Google-Cache-Javascript-Shor...

You can also write `cache:` in front of the URL. Works in FF, probably also in Chrome.

Looks like this is a Google search feature - didn't work for me in FF with DuckDuckGo as default search engine, but worked when I added !g to the end.

Re: The Facebook Algorithm Mom Problem

#165

Post by nkrisc »

kerbalspacepro wrote: post #138
Semaphor wrote: post #101

Earlier quoted context omitted.

I'm not sure if it is because of weird tastes or something else. But for sites like Steam, YT, Netflix I always wish for more tuning parameters because their recommendations are all horrible. On Netflix, for example, I get recommended stuff that's similar to other things I didn't like. Amazon is often the best of them for books because their engine seems to only really value the last few things I looked at / bought a…

Regarding Amazon: "Oh, you bought a wallet? Here are twenty wallets of the exact same type but with slightly different colors that you might want to buy, too"

My Amazon homepage is full of stuff I already own. Even worse is their internet-wide remarketing makes it so I see stuff I own on many of the sites I visit.

There was however one moment where Amazon got it right: they recommended to me a book that only a week earlier I had purchased on a whim from an independent bookstore with cash. Creepy good.

Re: The Facebook Algorithm Mom Problem

#166

Post by rogov »

krisdol wrote: post #75
ProblemFactory wrote: post #53

Earlier quoted context omitted.

> If you have a page, Facebook wants to milk you, so they've got this weird algorithm that pushes your posts to only a small fraction of the page's followers, expecting you to start "promoting" them. While this does enable Facebook to force brands to buy advertising, it is also an user-friendly change. Nobody who I have spoken to about this thinks that "like/follow" = "I want to see everything they post" on Facebook.…

Well "like" and "follow" should be different things. I follow users on instagram/strava because I want to see what they do. I like the content they post when... well, when it pleases me, or I want it to get some more attention. I deleted my facebook account after nearly 10 years with the service, but I hated the decision they made to show content from pages you've liked (often inadvertently when you meant to like a p…

They have changed this recently with respect to pages, so you can follow a page without liking it and vice-versa. However, the default still seems to be that like = follow. It takes additional action to decouple them.

Re: The Facebook Algorithm Mom Problem

#167

Post by CodeCube »

jon_richards wrote: post #149
wlesieutre wrote: post #141

Earlier quoted context omitted.

I told this story in the recent Amazon recommendations discussion, but I bought a pair of speaker stands from them and before it was even delivered they sent me an email saying "HEY BASED ON YOUR BROWSING HISTORY MAYBE YOU'D LIKE THESE OTHER 10 SPEAKER STANDS!"

I've heard the argument that this prevents buyer's remorse. Not sure if it has any merit.

wait, wouldn't this cause buyer's remorse? like, if I just finally decided to buy some product ... being bombarded with all the other options suddenly makes me rethink my purchase decision, "oh but what if this other one is more gooder!?!?!"

Re: The Facebook Algorithm Mom Problem

#168

Post by lostphilosopher »

kerbalspacepro wrote: post #138
Semaphor wrote: post #101

Earlier quoted context omitted.

I'm not sure if it is because of weird tastes or something else. But for sites like Steam, YT, Netflix I always wish for more tuning parameters because their recommendations are all horrible. On Netflix, for example, I get recommended stuff that's similar to other things I didn't like. Amazon is often the best of them for books because their engine seems to only really value the last few things I looked at / bought a…

Regarding Amazon: "Oh, you bought a wallet? Here are twenty wallets of the exact same type but with slightly different colors that you might want to buy, too"

"Amazon seems to think my recent purchase of an air conditioner was just the gateway to an air conditioner collecting hobby."

That's probably not exact and I don't remember where in my social feeds it came from, but I loved this.

Re: The Facebook Algorithm Mom Problem

#169

Post by patmcguire »

kerbalspacepro wrote: post #138
Semaphor wrote: post #101

Earlier quoted context omitted.

I'm not sure if it is because of weird tastes or something else. But for sites like Steam, YT, Netflix I always wish for more tuning parameters because their recommendations are all horrible. On Netflix, for example, I get recommended stuff that's similar to other things I didn't like. Amazon is often the best of them for books because their engine seems to only really value the last few things I looked at / bought a…

Regarding Amazon: "Oh, you bought a wallet? Here are twenty wallets of the exact same type but with slightly different colors that you might want to buy, too"

It's probably correct by expected value. You're just not the multiple wallet type. I'm sure there are people who'd want five wallets, eight different shoe styles, multiple cuts of pants...

Your indifference is subsumed in the sheer size of others' consumption.

Re: The Facebook Algorithm Mom Problem

#170

Post by jitix »

ryanbrunner wrote: post #95

I find a lot of sites feel like they're overtuning their recommendation engines, to the detriment of using the site. YouTube is particularly bad for this - given the years of history and somewhat regular viewing of the site, I feel like it should have a relatively good idea of what I'm interested in. Instead, the YouTube homepage seems myopically focused on the last 5-10 videos I watched.

I concur that.. these days I have to clear my youtube history every few weeks to prevent it from spamming my page (and my fucking TV!) with suggestions related to random videos I watched over a short period of time. The videos I liked over the last 7-8 years seem to carry less weight. I wish there was a way to tune these behavior.
Post reply on HN