How Twitter Rumours Evolve

The Guardian has a good analysis of selected rumours that were propagated by Twitter during the London Riots.

They’ve analysed 2+ million tweets based on their hashtags, performed a Levenshtein distance calculation across them all, and interpreted each as being either supporting/opposing/querying the rumour. The result is a moving graphic of how a rumour evolves.

Here’s another post on the London Riots

Selection Effects

An article on the BBC website just now regarding the London riots has caught my attention with the headline:

One in four riot suspects had 10 previous offences

And it goes onto say that:

Three-quarters had a previous caution or conviction

Is it really true that 75% of those committing crimes on those evenings had previous convictions, or is it that those with previous convictions have their details on a police database and it was therefore possible to identify (and find) those people based on images from photographs and recordings made last month?

Many people fail to notice when a selection effect (selection bias) is occurring, and in many situations. I remember many weekend nights out in my youth with my good friend John where he would observe that all the girls were going in the opposite direction to us and should we not go somewhere else. I stuck to the line that we were only ever going to pass people going in the opposite direction. It certainly wasn’t anything to do with us being uncool.

And here’s a good article on World War 2, regarding selection bias and aircraft design. An engineer was asked to inspect aircraft returning from battle over a period of time, and to come up with a recommendation on where to add armour. After building up a statistical model of where the aircraft he inspected has sustained damage, he recommended reinforcing armour in the parts that were generally not damaged. Can you think why? Answer under the fold.

Read more of this post

Post for the weekend: Your going to like it’s contents alot

One for my kid sister, a timely reminder of grammar mistakes that make you look dumb.

This guy really should have paid attention. There’s the underclass, and the bad in class…

Enjoy the weekend.

I predict a riot

Weapons, vehicles, and training notwithstanding, you only need a small number of your population (<<1%) to coordinate an attack and they'll over power the police:

Chart showing number inhabitants per patrolling policeman

The data for the graph is approximate and not all from the same year, but it’s not an order of magnitude out. I’ve split the force into 3 shifts and said that at any one time 1 in 4 of that shift are out of action (office work, taking suspects to the station, etc). I picked the EU5 countries, plus other English-speaking locations as comparisons. For the capital city, perhaps there are relatively more police, but my assumption would be that this would scale across countries. (Actually, the numbers for Haringey, a borough of London, come out to be the same for England and Wales). Overall therefore, the policing levels in London are not wildly different from other parts of the world, though perhaps on the low side.

So if 0.2% ish of the population across multiple extended geographic areas get upset and starts building wigwams, that could be hard to deal with immediately.

Taking 10% of a population to be male youth, it’s not hard to imagine areas where more than 1 in 50 kids are gang members – which gets us comfortably to 0.2% of the population.