In April I wrote for @ResearchDigest about @JEichstaedt's @PsychScience study linking heart disease to sentiments expressed on Twitter.
@sTeamTraen's critique has now been published in @thePeerJ https://t.co/9xxCVmEa0k https://t.co/b8FpAW1FJv
'There is no good evidence that analyzing Twitter data in bulk in this way can add anything useful to our ability to understand geographical variation in AHD mortality rates.' https://t.co/DYAeL4Ev2g By @sTeamTraen & @CoyneoftheRealm
How many different colours, apart from white, do you think are used in the maps in this figure? If your answer is 10, you might enjoy our new article: https://t.co/K0OZCkvgeZ https://t.co/EwD2bjpsoK
A highlight of our new paper ( https://t.co/K0OZCkvgeZ): The original authors omitted to mention in their article that the data that produced these "Twitter topics" word clouds were collected from *Facebook*.