I am gathering tweets on a specific location from the streaming API thanks to the python wrapper Twython. I am a bit surprised by the temporal patterns that I see so I was wondering if there could be any bias in the data collected. From what I understood, the API allows to collect roughly 1% of the requested tweets but is it uniform during a day? Maybe it depends of the number of requests and then could depend on night and day time, etc.
Any insight will be greatly appreciated.
I like to get an answer in this matter…too