Tweets about WI Gubernatorial Race Part I: October 28 to Nov 6

Politically, Wisconsin is quite different from my home state of New York. It’s long been considered a purple, or swing, state. For that reason, Wisconsin has often received extra national attention when it comes to local or state-wide politics.

The 2018 Midterm Elections were another example of this, with many citizens around the country tracking Governor Scott Walker’s race against Superintendent Tony Evers. Today, I explore how Twitter talked about this race in the week leading up to Election night (October 28 to Nov 7). This post will focus on the lead-up to the election. Part II will focus on the last few hours of the election (12:30 to 2:30 on November 7, 2018).

(Note: Tweets were collected using the r package rtweets. All datetimes have been converted to CST. For more information about this collection and analysis, please scroll to the bottom)

A broad temporal view: Oct 28 to Nov 6

In the week leading up to the election, there were several noteworthy spikes. We focus on two in particular: November 1 (8-9pm) and November 4 (7pm).

November 1, 2018 from 8:00-9:59 pm

This was the largest spike for Walker in this week (1568 tweets in two hours). Far and away, the most common verb used was variants of “call” (e.g., “called”/”calls”/”calling”). This is because, that day, Governor Walker said that President Obama was "the biggest liar of the world.” This language (employed by non-journalists and journalists alike) was also employed in leads of news stories in Fox News and The Hill).

November 4, 2018 from 7:00-7:59 PM

Although this peak was not as prominent as the others explored here, it is one of the few times that Evers exceeded Walker in references on Twitter.

Many of these tweets appeared to be campaign-oriented tweets about Evers’ support for Wisconsin residents. Unlike the previous spike, there did not seem to be an event aligned with this moment in time. This suggests that this spike was campaign-induced, rather than naturally generated.

A closer look at Election Day

As can be seen in the above image, attention to the Walker/Evers election peaked after 12:00 AM CST, late in the night relative to other well-watched races that day. Votes rolled in minute by minute, with many outlets (including NYT, one of my main trackers) showing a less than 1% margin for several hours.


Tweets were collected using Mike Kearney’s rtweets. I began my search at 2:40 AM CST on November 7, 2018, using the search terms “Scott Walker” OR “Tony Evers” OR “#wipolitics” OR “#wielection“. Twitter’s REST API provides an about 1% random sample of tweets. This yielded about 111,000 tweets.

Tweets were annotated for their part-of-speech and dependency using coreNLP. Within the corpus, there were over three million dependencies.

Understanding a little more about recent coverage of Korean-U.S. relations through adjective use

Yesterday, U.S. President Trump pulled out of a "highly-anticipated" summit meeting with North Korea's Kim-Jung Un. Given the freshness of this story, it'll take some time collect enough articles to do an anlaysis of this specific incident. But, in the meantime, some interesting results from my analysis of Korean-U.S. relations in American news below.

(Data cleaned and analyzed using R tidytext, quanteda, and OpenNLP. Graphs produced by ggplot2 or MediaCloud.)

Count of articles using the words "Trump" and "North Korea" in top American news media (digital + traditional). Results gathered using MediaCloud archive.

Count of articles using the words "Trump" and "North Korea" in top American news media (digital + traditional). Results gathered using MediaCloud archive.

As we can see above, the majority of the coverage appeared to be between May 7 (when North Korea claimed to have demolished a nuclear test site) and May 21. Using those two weeks as my window, I pulled all articles referencing "Trump" and "North Korea" from four news outlets: CNN (n =96), Fox (n = 114), the New York Times (n = 89) and the Washington Post (208), a total of 507 news stories.

I tagged all the words in the news stories for their part of speech using OpenNLP. I then pulled out all the adjectives, removed duplicates, and screened them for accuracy (OpenNLP has an above 90% accuracy, but the human eye is critical to ensuring quality results). I finally looked at the use of these adjectives in relation to specific actors/parties (mainly North Korea, South Korea, and the United States). Given the effect of political personalization, I consider both the country name and the name of the leader (e.g., "North Korea" OR "Moon Jae-In" OR "President Moon" OR "Moon Jae In") as keywords. I retained the adjective if it appeared within three words of the NK, SK, or US keywords.

Raw counts are presented below (keep in mind the corpus is not perfectly balanced... also, sorry I was too lazy to reorder the charts XD Just so tired and wanted to practice some code):

Most commonly used adjectives related to Trump/U.S.


Most commonly used adjectives related to Kim Jung-Un and North Korea


Most commonly used adjectives related to President Moon and South Korea