Looking at the Alexa stats for Wikipedia: http://www.alexa.com/data/details/traffic_details?q=&url=wikipedia.org
you see some interesting patterns. The graphs seem to have a sawtooth shape with a weekly period, but the specific days of the week where it peaks differ depending on whether you're looking at reach, traffic rank, or page views.
Raw page views seem to peak on Sunday and are lower at other times of the week, though there's a smaller second sawtooth around Wednesday. However, the reach statistic seems to be lowest on Friday and Saturday and peak around the middle of the week, with Sunday being an increase from Fri/Sat but not a major peak. The traffic rank follows the reach statistic, dipping on Friday and Saturday and holding steady at its highest level the rest of the week.
Can anybody venture any theories (original research!) about why this is the case?
On 01/04/07, Daniel R. Tobias dan@tobias.name wrote:
Raw page views seem to peak on Sunday and are lower at other times of the week, though there's a smaller second sawtooth around Wednesday.
Raw page views peak Sunday afternoon/evening US time. This is notoriously the busiest time on the site and is when you're most likely to hit a "sorry we're overloaded" message (though I haven't gotten one of those in ages myself). Not sure why there's a Wednesday peak as well though.
- d.
Use Alexa's comparison feature to compare wikipedia.org and google.com, they seem to mirror each other quite closely in terms of the sawtooth pattern.
I have no idea what it means, but it's worth noting.
Sunday, April 1, 2007, 11:47:07 AM, you wrote:
DRT> Looking at the Alexa stats for Wikipedia: DRT> http://www.alexa.com/data/details/traffic_details?q=&url=wikipedia.org
DRT> you see some interesting patterns. The graphs seem to have a DRT> sawtooth shape with a weekly period, but the specific days of the DRT> week where it peaks differ depending on whether you're looking at DRT> reach, traffic rank, or page views.
DRT> Can anybody venture any theories (original research!) about why this DRT> is the case?
On 4/2/07, Daniel R. Tobias dan@tobias.name wrote:
Looking at the Alexa stats for Wikipedia: http://www.alexa.com/data/details/traffic_details?q=&url=wikipedia.org
I prefer our own stats. The graphs are much nicer, and there's other data (which cluster the request is to, for example) which proves instrumental in my analysis.
This is the latest weekly graph for requests:
http://hemlock.knams.wikimedia.org/~leon/stats/reqstats/reqstats-weekly.png
...and here's the latest monthly graph:
http://hemlock.knams.wikimedia.org/~leon/stats/reqstats/reqstats-monthly.png
Note that the week (maroon line) begins on a Monday. The highest traffic is Monday to Thursday, and sometimes to Friday, with lower traffic on weekends. The weighted peak each day, across all clusters, is around 12:00 to 18:00 UTC.
Take a look at the weekly graph. You'll see that the knams and knams-img clusters peak earlier in the day, maybe 12:00 UTC, while the pmtpa and images clusters peak later, maybe 18:00 UTC. It's hard to see when the yaseo and yaseo-img clusters peak, but if you look closely, they peak at maybe 06:00 UTC. Lopar doesn't make it into the graphs
This might not make much sense until you consider that the pmtpa and images clusters are in Florida (pmtpa stands for Powermedium, Tampa), the knams and knams-img clusters are at Kennisnet in the Netherlands (knams is Kennisnet, Amsterdam) and the yaseo and yaseo-img clusters are in Seoul (yaseo is Yahoo!, Seoul).
My theory is that more people are using Wikipedia at work and during school hours than they are in their own time. The various clusters serve traffic closest to them at different times in the UTC day, but always corresponding to the local middle-of-the-day period.