Analysis of social metrics for twitter owner after some data centers went fully irreversibly cloud-based.
UPDATE: there is an update comment below. Each dot is a tweet.
Log scale makes the decrease a lot less apparent, but it is 5-10 fold across the board.
Edit: Just came to mind, that it isn't fully representative of the true expected decrease. Since posts would likely be viewed for days, or weeks, depending on algorithms. Data-wise, it should smoothly-ish decrease towards today. Guess time will tell.
For data set and code see: https://github.com/Eximius/sentiment-analysis-test
4 replies
I mean this would proof it was really a bot farm
Not entirely, the sample size of data is rather small. But the coincidence is... stronk.
Also, getting pissy at some very far away datacenters going poof feels self-incriminating.
Seems like a pretty healthy sample size for this effect size
UPDATE: I improved the botchy scraper a lot. Data is now much more nice. With a bigger sample size.
The only things that are visible: Dip from Oct 9, but genuine unpopularity / noise can explain it. The strong dip of views from Oct 9 that did not stop: might actually just be ruski bots that were scraping the twitter owner for financial advise and/or other.
Seemingly, nothing new on the western front.