Will.Whim

A weblog by Will Fitzgerald

Distribution of tweet lengths

% of English tweets by size (sample 50k)

I get a very different distribution of tweets than Isaac Hepworth — no spikes at 28. My provisional guess is that his data is a bit wonky. My data here is (only) 50k English tweets from one day in 2007.

Isaac Hepworth's distribution

Advertisements

3 responses to “Distribution of tweet lengths

  1. CogitoErgoCogitoSum January 8, 2012 at 10:53 am

    Its also possible that over time that peak has gradually shifted to the right, and now this theoretical peak is at greater than 140 characters. Personally, I think twitter should start accommodating larger tweet sizes.

    • Will Fitzgerald January 8, 2012 at 2:23 pm

      Sure; the main difference to my eye was the lack of peaks near 30, and the small amount of variability for the long stretch. Isaac has stated that the peaks were an artifact. The overall shift to the right might be there, but it would require a bit more investigation to find this out, and some historical data, which is hard to come by.

  2. Pingback: Distribution of Tweet Length – My version » Han Xiaogang's Blog

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: