A wedding and a funeral

I began thinking about the Facebook graph.  While, like Tony,  I am disappointed in what they gave us, I have realized there is some useful information.  In this case I am looking at the month of May.  Here we had the royal wedding and the death of Osama. While its not clear, because of the way of the data is presented, I think we can infer some key elements of memes.

1. These two memes are the only ones overlapping in 2011. 
2. The marriage begins to spike before Osama's death 
3. The royal marriage ends its spike just as Osama's death is reported
4. So we can possibly be seeing one meme stealing the audience of another.  

This theft is important because it shows how one meme spikes at the expense of other conversations.  But until we get data with more fidelity we can only infer that Osama's death stoled audience away from the royal wedding.

The other thing we should take notice of is the type of memes the spikes represented.  They all seemed to be call to celebrate, mourn or pay attention to something.  They evoke an emotional response to share.  

Finally a bit about natural level of conversation.  While we can not see the day to day changes in the conversations we do know they exist both from observation but also from the data.  As Tony pointed out Facebook broke the data into 4 subgroups and each group came with top ten stories.  This gives us 40 stories that did not spike, so we can infer a level that has to be less than Irene spike that stays pretty stable since it can absorb 40+ events without spiking.  

Facebook's top ten memes of 2011

They gave us a link here and you can find the global memology and the US-specific memology.  The Y axis is labelled "Status update mentions ranked by growth (2010 vs 2011)." There are several small upticks in conversation that happened without making them into the top 10.  They show actors, movies, tv shows, and fictional characters' ranks, too.  The added tabs for music, sports, and news.

One might notice how many new conversations were struck up for these top-10 events by examining the difference between pre/post-event chatter and the chatter in the event itself.  Some factors that we can consider influencing the difference include:

• lurkers making a post for the first time in a while
• actual discourse
• people joining Facebook just to talk(?)
• lots of reposts, copy/pastes, or likes (we do not know that like button hits are counted; are likes status updates or not?)

It is unfortunate that the full range of chatter-- what one would see on a normal basis-- is either so small that it is occluded by the large spikes (logarithmic Y axis would have helped here) , or was not actually included in the data.  Perhaps when they say "2010 vs 2011" they mean subtracted conversations of 2010 from the 2011 data, ignored negative numbers (those would be events in 2010) and showed only peaks above a certain threshold (removed noise).

Oh for the raw data.