Live data from Hacker News

Introducing Graph Search

facebook.com

111–120 of 266 posts

Re: Introducing Graph Search

#111
post #60

I think this a big deal. The first step to a Yelp killer? Type in "Italian Restaurant" and get back list of all the restaurants your friends have checked into. A recommendation engine. For now, its mostly to filter your facebook data. But do you think it can expand and become the goto search engine, ala google?

It could maybe work if they do it like Netflix: build a profile of you based on what you have rated highly, and put you in a pool with similar people (friends or otherwise), thus providing more accurate recommendations.

But I think Facebook overhypes how much people care about their friend's preferences, at least for most things. We generally don't pick friends based on how closely their shopping/eating/whatever habits match ours.

Re: Introducing Graph Search

#112
post #86
post #59

Earlier quoted context omitted.

That's where other social networks differ. On Diaspora for example one probably doesn't know anyone after joining, and you always meet new people. You follow interests, subjects and conversations, not your acquaintances from real life. So it may be "big" for Facebook, but it's routine for other networks.

It might be a routine for others but the big thing here is that facebook found a way to do it and there are a LOT of people already on facebook. That will then make facebook the biggest and most efficient site for this feature.

Hashtags work for that quite successfully (in Twitter and Diaspora). I'm not sure how well will these graphs work in comparison, but it's better than nothing for Facebook.

Re: Introducing Graph Search

#113

This is an important step for Facebook and I'm surprised no one has really mentioned it (all ~50 comments so far are about the graph search). The big thing here isn't graph search, or the fancy searching per se. The big thing here is this: > "and meet new people, too." This is huge. Huge! Facebook from the start was envisioned as a sort-of dating platform but that part of it got swept under the rug real quick. Throug…

Sorry but mimicking meetup.com is not a big thing. Very few people like to meet up with strangers regardless of similarities in hobbies/activities. This will cater to a niche crowd and that will be it. This is a great feature on Facebook but let's temper the excitement about its importance.

Re: Introducing Graph Search

#114

This is an important step for Facebook and I'm surprised no one has really mentioned it (all ~50 comments so far are about the graph search). The big thing here isn't graph search, or the fancy searching per se. The big thing here is this: > "and meet new people, too." This is huge. Huge! Facebook from the start was envisioned as a sort-of dating platform but that part of it got swept under the rug real quick. Throug…

> This is huge. Huge! Quite the opposite, in my opinion. People don't like being bothered by strangers on Facebook. It's weird and creepy, especially so when it's a guy contacting a girl. This could be seen as a disincentive to share if you don't want your face popping up on search results for people outside your immediate network. It also makes friends who are ignorant or careless about privacy more of a liability.…

>Then again, that could just increase the amount of noise on Facebook and drive people away even faster.

How is this any different to just creating an event normally ?

Re: Introducing Graph Search

#115

Earlier quoted context omitted.

Replace "grandma" with "person whose taste in sushi is very different" if it makes you feel better.

Mmmkay, so out of 3 ways to implement ranking: 1) Rank by popularity among all friends. 2) Rank by global number of check-ins. 3) Rank by a one-off friend's preferences. You think (3) is the way something called GraphSearch works?

This is a great strawman that you've knocked down.

I think it's closer to #1 with "popularity" replaced by "preferences". But that has the problem that i don't care what all of my friends think about most things, or even most of them.

Re: Introducing Graph Search

#117
post #32
post #8

Earlier quoted context omitted.

I'm watching the demo.

What makes you think that Facebook doesn't calculate an affinity score between each pair of friends and use that to heavily weight search results? The affinity score definitely exists (EdgeRank), and it seems to be used all over Facebook currently, so I suspect it would be a big factor in search.

Single affinity scores would not be very effective since my affinity towards various friends varies with different queries.

You'd need a very large matrix of combinations, which would be really expensive to build, and probably really expensive to use during scoring.

I'm guessing they use something similar to this with a bunch of other ranking signals. I guess i'd just be really surprised if they've actually made it work well.

Re: Introducing Graph Search

#120
They're going to have the same problem wolfram alpha has, since in the space of "all queries" only a tiny, tiny fraction of them are going to be ones that Facebook can resolve. Now, it might be less of a practical problem since the use cases for FB search are pretty clear and obvious, unlike W|A. But it doesn't sound like this is an open-ended search engine. Imagine typing say "shoes for sale on amazon" and getting "Sorry, Facebook doesn't know how to answer this query." It will quickly pigeon hole the product.

Also, similar to W|A, there is value in the queries themselves since they are mini-algorithms. If someone comes up with a clever query to get FB to say, find me people who I actually might want to hire, it could be valuable. I really hope they build an API on top of this so that startups can build products around novel queries.

Post reply on HN