The Relationship Test
dataclysm.orgI'm getting this response from facebook:
{ "error": { "message": "(#4) Application request limit reached", "type": "OAuthException", "code": 4 } }
Looks like they've drilled facebook a bit too hard. Any chance Christian Rudder will open source this so we can run with our own app tokens?
Shame - I was curious how this would compare to facebook's internal friend ranking (discoverable through methods such as this: http://thenextweb.com/facebook/2013/11/10/script-shows-faceb...)
This is the (jsbeautified) source of the script from your article (http://pastebin.com/kvvYXKKX). I'll wager grammar_costs is just a metric used by graph search and not your friends' coefficients.
Hmm, I'm not entirely sure I understand the "assimilation score". My partner Sarah is at the top, which makes sense, but then some people I barely know (brother of an ex, etc) are like #3 and 4, even though we only have two mutual friends. I have approximately 1,000 friends on FB... so maybe that's broken something?
Similar questions here, and I have much fewer Facebook friends (around 350). My wife is #1, and it's not even close (66560 compared to #2, who is 8145).
But after that, I have a few people I don't care at all about in my top 10 (I'm thinking of just removing 3-4 of them now that I see that they're still my friends), and a couple of my closest friends have a score of 1.
From the linked paper [1], it looks like the scores are calculated based on a concept of "dispersion", which is how closely a particular individual in your network is connected to each of the separate clusters of people you know.
Each of the clusters in the graph represents a "social foci", such as co-workers, high school classmates, college classmates, etc.
The dispersion score calculates how well someone you know is connected to these multiple disjoint clusters of people in your life, and tries to show that the person with the highest score is most likely to be your romantic partner.
This probably doesn't work so well in trying to identify friends, since it's likely that a close friend from college may not know any of your friends from work, or your high school classmates.
I think this had a field day with my disparate groups of ~300 friends/family. I have two huge clusters of school vs work, with school split into high school vs college, and 4 smaller, fuzzier clusters of other groups (gamers, irc buddies, 2x family). My husband came in first with a score of 1310000+ with our roommate second at 343000+.
Most of the next 20 people or so (scores >30k) are people we invited to our wedding that we found out later friended others that attended our wedding, or are people part of multiple groups (tech people that I game with). I'm not sure I'd call these people more central to my life just because they're more social though, after a point.
Number 1 is my brother, which makes sense. He knows many different groups of my friends.
Number 2 is a friend who's a movie producer, ie a professional friendmaker. He's got a zillion friends.
After that it's kind of random.
Three of the women I've actually dated are literally at the bottom of the list. Makes sense, several times I've dated completely out of my circles. Funny to see though.
What's weird is that one of those women's friends, who I otherwise don't know at all, is near the top. Well above the woman I actually dated. We have no other friends in common. Interesting.
Same here. Top three are partner, mother and sister. Makes sense. 4 is someone I haven't talked to in 8 years and barely know.
From a quick skim of the algorithm paper, here's what I understand of how it picks "high assimilation score" people:
1) look at all links to mutual friends; categorize friends based on their connectedness to different clusters (ie, "school friends", "work friends", etc.) 2) look for friends who are mutual friends with people from multiple clusters (people who know both your family and your coworkers -- "bridge friends") 3) look especially for friends who are friends with multiple people from category 2 (people who know most of your bridge friends)
The assumption seems to be that people who are peripheral friends will only know others from one circle. People who are somewhat close will know others from multiple circles. And people who are the closest to you will know a lot of your multi-circle friends.
(FWIW: this put my wife well ahead of anyone else, but the rest of the ordering seems barely better than random. A guy I played video games with a couple times back in 1998 is #2 by a large margin; the guy from the same video game who my wife and I hang out with several times a week and who co-runs some major projects with us scores less than 1/4 of that. My dad clocks in just behind the new youth pastor at my church who I've known for all of two weeks.)
Yeah it seems like it is also a bit zero sum - the higher your 1st match is the lower the rest will be.
This probably happens because if your partner has a large number of connections to the other important people in your life, your partner (/person with most connections to all the various groups) then absorbs all of those people, leaving only people with no connection to those groups to take up the runner up spots.
'Inanimate carbon rod', a page that was a friend's joke and has never had any posts, came 8th on my list.
Well, that's a Simpsons joke[1], so maybe it's popular because of that.
I think it makes sense that your wife (or SO) would score very highly; if someone is close to you, you typically introduce them to friends, family, co-workers.
A more interesting question would be to ask if it has any predictive power.
Though, also, FWIW, I can't get it to run (getting an error already reported in another comment).
Hmm, I'd take it with a grain of salt, without knowing how the score is calculated. All of my closest friends are ranked way, way down the listings.
I do see four distinct clumpings, with very little overlap: my large, extended family, the people I went to high school with, people I knew in college, and the small group of coworkers I have now. Which is kind of interesting, but also makes total sense, since those are completely disjoint sets of people.
"it will show you ... which of your friends are most mathematically important to your life."
Interesting use of the term "mathematically" to cover the likely difference between the model and reality.
And the only purpose in participating, as far as I can tell, would be to understand how close their model can come -- by definition, I almost certainly know who my important relations are.
#1 is my wife, by literally an order of magnitude. That's about right; we have a truly extraordinary relationship.
After that, unfortunately, this ranking is nonsense. #2 is someone I met once and have never communicated with since. We have only one friend in common. Totally bizarre. My good friends are scattered between ranks 5 and 50, amidst a sea of near-strangers.
> That's about right; we have a truly extraordinary relationship.
A relationship like this is what I want more than anything else in life, so I hope you don't mind me derailing the conversation a little bit to ask: to what do you credit with getting along so well? My parents also had an extraordinary relationship (before my mother passed away), and I'm always interested in figuring out what exactly it is that makes some couples so happy together.
For us, it's that we're extremely close friends (we were friends for some time before dating), we both have a tremendous respect for one another, we have the same (fairly dark) sense of humor, and when we found each other we both knew how lucky we were and both were willing to upend all of our previous individual plans for life in order to be together.
None of that is a reproducible formula for a perfect relationship, and honestly my personal track record wasn't great before finding my wife. Really the only advice I have is to find someone that's not just a significant other but a very close friend -- a lot of people say that, but not many truly have it -- and, when you find someone like that, put her (or him) before absolutely everything.
Thank you for the advice! It means a lot.
I also had it pick out my wife by an order of magnitude over everyone else -- and that's the best I can say for the rest of the list: it included everyone else. I can't see any particular order or pattern there. My last place, theoretically most unimportant connection is actually a good friend of mine I interact with regularly offline.
Exactly the same here. #1 is my wife and #2 is a relative stranger, which I should actually not have on Facebook. Probably a bug.
Similar results here.
#1 is a close friend
#2 is some random that I should probably not be friends on Facebook with added a week or two back. Acquaintance at best
#3 is someone I've not spoke to in years
#4 is the SO
#5 is another person I've not spoke to in years who is friends with #3 if that means anything to anyone scouring comments for bugs
#7-11 are randoms that I've spoken to a couple of times "keep in touch!"
#12 is in my reality #2 spot after the SO, very close friend we speak pretty much daily and all that
Same here. #3 is my friend's dog. She's cute, but I've never met her. We don't communicate much either.
#1 is my ex, #2 and #3 are guys I barely know. After that, the top 10-20 are just the Facebook friends that are most active on Facebook.
That's interesting because #1 is my ex (who's not too active on Facebook), as well. But #2 is my cousin who is hardly active on there. #3 is someone who is kind of active but I never hung out with much.
My current girlfriend, who is not active on FB at all (she's more of a lurker), is basically last, with only 1 assimilation point.
I only have a little over 100 friends, though.
It's not much of a temptation for me because I don't have a fb account but whenever I see facebook apps that promise to give you something in return I'm always reminded of this:
I don't want to take the lollipop, but I do want to know what happens when someone else does. Share spoiler?
It's a video of a "dirty" guy on a computer in a rusted warehouse, browsing facebook on a computer. It pulls up your info and shows him scrolling all over it, looking at pictures, etc, and then he Google Map searches your hometown. There's a shot of him driving, with cuts of him in the hollywood-style "freaking out" thing, and then he gets out of the car with either a knife or a gun, and it puts your profile pic on a piece of paper taped to the dash.
So, somewhere between reality and fear-mongering.
To describe it would be to ruin it. Take the lollipop.
That was what I expected in the most amazing way.
Don't be a wuss. Take it!
My co-founder is rated more 'central' to my life than either than either one of our's significant others.
It is quite good at grouping different sets of friends visually (ie, high school friends, university friends, friends from different hobbies and sports, work friends, etc).
Not sure if anyone else encountered this, but some of the data listed for mutual friends is wrong. It often listed less mutual friends than I had in common with many people, sometimes by 10+ people.
The person I have the highest assimilation score with is someone who I've never talked to in my life, and I only accepted his friend request(really recently) because we had a few mutual friends.
Something strange: I revisited my results an hour later and the order seems to be different. In some cases, a friend has gone from rank ~20 to 10.
My only guess is that people are adding/removing friends which changes things around, but that seems to be quite a difference.
Edit: For what it's worth, the listing seems very accurate for the top 10, which is comprised of my best friends, my sister, a couple old girlfriends. Things get a little weaker after that.
Rankings can seem to be unstable if the absolute differences between the scores are very small relative to the likely ways those scores could change.
Example:
Rank,Score
1,0.81
2,0.541
3,0.540
..
40,0.538
Increasing the value of row 40 by just 1% will cause it to go from rank 40 to rank 2.
Edit: Improved formatting.
I kinda liked the graph (i suppose it's made up with Graphviz right?) because it could sort out different groups of my friends eg. my first and second Erasmus friends were two separate groups, friends back from my hometown were another one, and another friends from a training course i had participated lately. But the assimilation score list was totally off the point. The first ten people i got are still friends but not that close to me.
It's interesting that this came along just a couple weeks after LinkedIn Labs turned off InMaps (their visualization and clustering of your linkedin graph): http://help.linkedin.com/app/answers/detail/a_id/4949/~/inma...
My 4 best friends in the world rank (well there are 5 but one quit Facebook): 1st, 6th, 13th, and 40th; 18th already begins in with people I kinda sorta don't like or am at least ambivalent about.
Needless to say, it is a mess and doesn't support people who have lived in different places all that well LOL.
A close friend got first place. Good show. Second place is someone I hardly know: the post doc on my dissertation project's wife. I think I've met her IRL twice. Second is worse than that. At the bottom are people I speak to on a daily basis, or am biologically related to. Fail.
#1 is some guy i went to high school with which I never talked to that much... weird, #2 is some guy I don't particularly like. My girlfriend is at ~30 and my exes are in the top 20. I don't think that app is particularly revelent in my case (most top 10 are people I barely know).
A lot of the "mutual friends" numbers are incorrect for my friends. Maybe a permissions thing?
Throws an "Uncaught SyntaxError: Unexpected token u" at line 224 (mutuals = JSON.parse(arguments[i][0][j].body);)
Same for someone else? Waited quite a long time (comments here said it takes long) and then opened the console.
same error here...
Runs forever on both Chrome and Firefox for me.
WAY off for me. My top 10 include a good friends brother (whom I have very little contact with), and two people I dislike somewhat strongly and have had no contact with for at least 5 years.
The top spot makes sense for me but everything else makes no sense whatsoever. How can someone I have only 2 friends in common with come in second?
My top ten contains five people who I barely know.
My wife is #1 on the list, then just curiously, I scrolled to the bottom. The last 3 spots are populated by ex's.
It bugs when you have more than 1000 friends the scripts takes too long and freeze the browser ....
Nothing useful for me. Way off.
Can anyone give a basic description of the assimilation score?
Nice, but the UI lags too much for me. I have ~200 friends.
Agreed - if ever there was an example of why performance matters on a web app. I gave up after the spinner was still spinning after I had navigated away and back (and replied to 5 emails)