Facebook Graph Search: I got it, I even queried the author – but I don’t get it yet

Facebook’s new graph search is in closed beta at the moment.  I managed to hurl myself onto it  before the door shut.   I played around with it for a while, then I stopped, waiting for inspiration about how to make it as interesting for me as I was sure it was going to be.  I  haven’t figured it out yet.   So when I saw that the lead engineer from Graph Search, Kari Lee, was giving a Facebook Tech Talk this evening at Facebook’s London office, I hurled myself at the guest list, and squished myself on before the door shut.

My problem is not that I’m uninterested in graph search.  I think it’s fascinating.  Honest.  I even know more than a bit about it, and I still think it’s fascinating.   And I am convinced that for Facebook, the potential here is huge.  Beyond huge.  I am pre-sold on that.   It’s just that, as currently constituted, Facebook’s beta version doesn’t do anything for me.   I do wonder occasionally what I should ask of it.  And fail to engage myself.  Then I try not to be parochial and I think of myself as not being myself, but being at different life stages, doing and wanting different things.  So far, it hasn’t helped.

Facebook’s graph search icon

Facebook’s previous version of search was awful.   I blamed this on Bing, rightly or wrongly.  So, with graph search, I was looking forward to seeing something that shone a headlamp into the murk of the future, even if it what was illuminated wasn’t already a polished jewel.

The content of the talk this evening focussed almost entirely on the natural language processing done by the query constructor, which is impressively free form, and does a lot of “search ahead”, which, given the nature of the data it is trying to reach, is not trivial.  It’s all also updated in real time.   A lot of heavy lifting had clearly been done: they showed a picture of Kari’s team fillling up a massive “statement” staircase.  Mention was also made of how the indexes were stored.  I did wonder how much sense the talk made to much of the audience, as the majority had not been able to cram themselves onto the beta – possibly because they were ineligible as they spoke UK-english, which is not yet supported.  (I’m not sure how or why FB inferred that I spoke US English as one of my dialects.)

Kari went into considerable detail about their strategy and approach for query NLP and UI.  But, to my mind, the talk wasn’t about graph search.   I really thought it was about a front end to graph search.  I asked her about this, as best I could.  I thought she was treating the problem as if it was entirely about query resolution, and the problem ended there.  She answered that what she did was the parser, and that was what she talked about.   Which was certainly a straightforward and honest answer, but it left me feeling rather puzzled.  I think the good bit’s the next bit.  And by that I do not mean the cleverness of how it’s all distributed.   I mean what it does.

Facebook clearly are into graphs from an algorithmic perspective.   That was, in a way, the subject of their recent Kaggle competition which they are using to try to hire more data scientists.  So my bet is that someone, somewhere inside Facebook is thinking about it.  It just hasn’t been surfaced yet.   Graph search, as it was presented this evening,  is already being used internally in Facebook, in two products (ie. services) currently in development.    So we’ll see more of it.   Perhaps what it most needs is a context.  So I look forward to seeing more about how that develops.

[You may have noticed a recent blog theme of “stuff I see while wandering around London at night”.   (You’d be right…:-)]

Facebook says it isn’t an echo chamber. But is it a hall of mirrors?

Putting aside for a moment from the actual questions the Facebook Data Team asked and the answers they got, both of which are interesting (so I will try to get to grips with them – in a later post),  I think the most surprising thing about this study is the fact that Facebook publicly used itself as an experiment,  and nobody blinked.    What they did in the study was only a tiny, weensy bypass operation.  (The experiment involved  withholding some newsfeed items from its users that they would normally have seen as result of the operation of the service.)    But it was surgery none the less.

My own private speculation is that Facebook experiments on itself all the time, and then quietly gets on with applying the lessons it learns by doing so.   But the Data Team’s world-facing work is usually correlational and observational rather than directly experimental.  So this work is different: here, they did tweak around with Facebook, and they did publish their results.  And I am surprised that nobody seems to be interested in that fact.  I don’t have an issue with the fact they did it.  In fact,  I’d be a bit disappointed if they didn’t.  But then I’m an experimentalist by background.

Don’t get the wrong idea: I do care whether I see stuff that’s sent to me.   When I get the post delivered from the postman each morning I don’t expect him to randomly hide some of it from me just to see what would happen.    Interestingly I have heard more than one story in which it turns out that is just what (a few lone and deranged) postal workers sometimes actually do.   But although this isn’t unheard of, at least as an urban myth,  it’s not what I expect, and were the behaviour to be discovered, I would expect it to be stopped.   Ignoring my post is my job, not my postman’s.

But my view of my Facebook Feed is different.  My understanding of my Feed is that it is cooked up according to a secret sauce recipe which, although it isn’t exactly to my personal taste, represents Facebooks’ best efforts at optimising something of interest to it.   And I believe the recipe for this sauce is constantly evolving, although the brand remains the same.   So to find there has been a tiny systematic tweak made to it, whereby some information was hidden for some people when it would normally have been displayed,  is neither a big shock, nor a bad one.

What surprises me about it is that it seems to have been so generally unsurprising.  I have a few different theories about this:

1.  the Eric Reis theory

The Lean Startup ideas of Eric Reis have become so pervasive and “baked into the DNA” of our culture that everyone who thinks about the matter expects to become part of some massive multivariate test whenever they encounter any application or platform.

2.  the filter bubble theory

Nobody who would potentially have been offended or puzzled by having their NewsFeed tweaked around with actually understood what was happening.

Here are some screenshots I took this morning about the relative numbers of people who publicly lauded the research summary, versus the full research article.

The score is as follows.   There were over 5,000 social actions performed on the summary.   And 165 on the article itself.

3.  the common sense theory

The change made was so non-material in its potential and actual impact that nobody in their right minds could possibly make a big deal of it.

So, no shortage of theories.  But I’ve no idea which one is right.   Do you?    My guess about the recipe is:  20% Theory 1, 60% Theory 2, and 20% Theory 3.

The highly munchable and crunchable soundbite about the study, distributed with the summary ,  was that the research demonstrates that Facebook is not an echo chamber.   This meme has bounced around languidly, albeit dominantly,  following the release of the research.   I believe that the research, while interesting, does not actually warrant this conclusion directly.   But what the research does demonstrate, by its very existence, is that whether or not Facebook is or is not an echo chamber, for sure it sometimes acts like a hall of mirrors.

Source: ItDan - Flickr