Cracking The Code On Trump Tweets (time.com)

jIyajbe writes: From Electoral-Vote.com: "A theory has been circulating that the Donald Trump tweets that come from an Android device are from the candidate himself, while the ones that come from an iPhone are the work of his staff. David Robinson, a data scientist who works for Stack Overflow, decided to test the theory. His conclusion: It's absolutely correct. Robinson used some very sophisticated algorithms to analyze roughly 1,400 tweets from Trump's timeline, and demonstrated conclusively that the iPhone tweets are substantively different than the Android tweets. The former tend to come later at night, and are vastly more likely to incorporate hashtags, images, and links. The latter tend to come in the morning, and are much more likely to be copied and pasted from other people's tweets. In terms of word choice, the iPhone tweets tend to be more neutral, with their three most-used phrases being 'join,' '#trump2016,' and '#makeamericagreatagain.' The Android tweets tend to be more emotionally charged, with their three most-used phrases being 'badly,' 'crazy,' and 'weak.'" reifman adds: In an excellent forensic text analysis of Trump's tweets with the Twitter API, data geek David Robinson demonstrates Trump authors his angriest, picture-less, hashtag-less Android tweets often in the morning, while staff tweet from an iPhone with pictures, hashtags and greater joy mostly in the middle of the day. Robinson's report was inspired by a tweet by artist Todd Vaziri. As for why Robinson decided to look into Trump's tweets, he told TIME, "For me it's more about finding a really interesting story, a case where people suspect something, but don't have the data to back it up. For me it was much more about putting some quantitive details to this story that has been going around than it was about proving something about Trump's campaign."

Comments

Re:Thanks Media

[Anonymous Coward]

> The reason you never hear about this is not because it didn't happen or because nobody was looking for it.

The reason you "never hear about this" is because your interpretation of those events is nutballs.

If your "liberal media" theory were true, then there are a ton of counter examples. The whole lewinsky thing being chief among them. The obsessive media coverage of clinton "scandals" is beyond dispute. Travelgate, whitewater, vince foster, benghazi, etc. And despite tens of thousands of hours of media coverage, and tens of millions of republican directed tax dollars of investigations, it all turned out to be nothing. Cry wolf too many times and people just start tuning you out, no "liberal bias" necessary.

More Interested in His Code

[jIyajbe]

I'm one of the two submitters. I submitted this story because I am intrigued by his methodology, and not because of the political angle.

In my submission, I included a reference to the fact that he coded up his analysis in R, and that his code is right there on his website for all of us to inspect. I was hoping that that was what would catch Slashdotters' eyes. The editor deleted that part, unfortunately; oh, well.

I know a little about statistical analysis, a little bit about coding, but nothing about R. Can anyone knowledgeable about R comment on his code, and/or his analysis? Thanks!