Finally looked at the OKCupid paper, and their data collection methodology is a bad joke.pic.twitter.com/9BbWtxDU9p
-
Also, I wouldn't have released the dataset with the usernames.
We kept usernames for 2 reasons: 1) forgot to scarpe some data, so using them others can get the rest later if they want to.
-
-
2) the usernames are an interesting topic in themselves -- what makes someone use e.g. "hot" in their profile name?
-
And sure, usernames can be interesting. I wouldn't have released them, especially as part of the same dataset.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.