Textanalysis of Drumpf-Tweets: Orange Android is angry

Gepostet vor 10 Monaten, 13 Tagen in #Politics #Science #Tech #DonaldTrump #Language

Share: Twitter Facebook Mail

Data-Scientist David Robinson hat sich die Tweets von Donald Drumpf angesehen und anscheinend kommen alle nicht-agressiven, non-hyperbole Tweets, Danksagungen oder Event-Hinweise von einem iPhone (seinem Team), alle Angriffe, Beleidigungen und Whatnot kommen von einem Android-Phone (Trump selbst). Diese Teilung ist auch hinsichtlich zeitlicher Intervalle und Retweets konsistent: Trump twittert vor allem morgens, sein Team gegen Nachmittag. Trump retweetet manuell, sein Team tweetet viel mehr Links und Bilder.

Dann hat sich Robinson die Sprache der Tweets angesehen. No surprises:

Trump’s Android account uses about 40-80% more words related to disgust, sadness, fear, anger, and other “negative” sentiments than the iPhone account does. (The positive emotions weren’t different to a statistically significant extent).

We’re especially interested in which words drove this different in sentiment. Let’s consider the words with the largest changes within each category:

words

This confirms that lots of words annotated as negative sentiments (with a few exceptions like “crime” and “terrorist”) are more common in Trump’s Android tweets than the campaign’s iPhone tweets.

Und hier wird es interessant, es gibt anscheinend einen iPhone-Tweeter in seinem Team, der die Sprache Drumpfs imitiert. Ein Trump-Ghosttweeter:

The majority of the tweets from the iPhone are fairly benign declarations. But consider cases like these, both posted from an iPhone: „Like the worthless @NYDailyNews, looks like @politico will be going out of business. Bad reporting- no money, no cred!“, „Failing @NYTimes will always take a good story about me and make it bad. Every article is unfair and biased. Very sad!“

These tweets certainly sound like the Trump we all know. Maybe our above analysis isn’t complete: maybe Trump has sometimes, however rarely, tweeted from an iPhone (perhaps dictating, or just using it when his own battery ran out). But what if our hypothesis is right, and these weren’t authored by the candidate- just someone trying their best to sound like him?

Dark Stock Photos

My favorite Tweetie-Bot for the next 5 Minutes: @darkstockphotos, „Extremely fucked up stock photography. An @ultrabrilliant abomination.“

A Stephen King-Story of 2 Presidents

I find this far funnier than I should: „Stephen King has now been honored by two U.S. presidents: National Medal…

Gun-Emoji Pairings 🔫😶

Interesting analysis of the Gun-Emoji-Pairings: „What does the Gun shoot at?“ and „Who pulls the Trigger?“

The Power of Language

„In this reel, we explore the incredible power of language—written, spoken and performed. First, meet the creator of Game of…

Anthony Burgess lost Dictionary of Slang discovered

Die International Anthony Burgess Foundation in Manchester hat neulich das verlorene Slang-Wörterbuch von Anthony Burgess im Keller gefunden („at the…

Neural Network Genesis Alpha

Douglas Summers hat das erste Buch Genesis der Bibel mit Neural Network Voodoo in Worte übersetzt, die allesamt mit dem…

Tweets of Trouble

I find this far funnier than I should. (And I'm not convinced this is a photoshop. Differences in the same…

Reality leaks

The Intercept veröffentlichte gestern neue NSA-Leaks mit Beweisen für Wahl-Hacks der Russen. Direkt nach der Veröffentlichung wurde nun eine Frau…

British Power Slave tastes like real Rockstar Testicles

Poster und Flyer am 10 Pfund bei Wankers of the world. (via @b3ta_links)

Podcasts: Sid Vicious, Baudrillards Simulacra, das Wörterbuch der Unruhe und das Märchen vom unglaublichen Super-Kim aus Pjöngjang

Jede Menge Podcasts und Hörspiele, die ich in den letzten Wochen gehört habe, unter anderem ein Hörspiel um einen mutierenden…

Climate Agreement Pullout-Playlist

Daily Beast-Writer Asawin Suebsaeng a couple of minutes before Trump pulled out: Military jazz quartet accompanying Trump's Paris pull-out announcement…