By Andrew Jeavons
I decided it might be interesting to analyze the tweets of the main political players in the run up to the last 3 sets of significant primaries. The methodology was simple, follow their official twitter accounts and then analyze the tweets for emotional word content. The analysis was done the 29th February, 8th March and the 14th March. Each analysis contained the previous 6 days tweets by each candidate. A break down of the volume of tweets per politician is shown below:
Obviously there were a huge amount of other tweets relating to the individual politicians but I wanted to see what their core message was in terms of the use of emotionally related words. It’s of note that Cruz , the youngest of all the candidates, sent out the most number of tweets, followed by Sanders. Cruz was also the only one to use no capital letters in his screen name “tedcruz”. The level of tweeting seems high and stable for Cruz, but within the last week the tweeting by the other candidates has dropped off.
Words were categorized using 8 types of emotion, which could overlap. The types were fear, anger, sadness, disgust, anticipation, surprise, joy and trust. It’s a simple approach which treats text as a “bag of words”, no attempt is made to parse the text for sentiment.
As an example I searched for the word “food” in a collection of 1.5 million random tweets. The search revealed 7319 tweets with this word in them, the analysis of these tweets for emotional content is shown below:
This ring is like a pie chart, except it’s thickness is in proportion to the numbers of words which could be classed as emotional out of all the words in a tweet. The percentage in the center is the value for this, so 33% shows that 33% of words in the tweets with the word “food” in them could be put into one of our emotional types. This is a measure of how emotionally expressive the tweets were. The circle on the lower right shows the percentage of emotional words that are either classed as positive or negative within all the words classed as emotional. Blue means positive, red means negative. In way of contrast a search for the word “death” shows a very different result:
In term of the candidates’ tweets, if we look across the analysis we can see the some patterns :
The top three emotional categories for Clinton and Sanders are trust, anticipation and joy. For Cruz and Trump they have the same top two, trust and anticipation, but differ in the third highest. For Trump his third category is sadness, for Cruz fear. Sanders and Trump have the highest level of emotional words, with the others at pretty much the same level.
The next analysis is slightly different:
Top emotions for Clinton and Cruz are still trust, anticipation and joy. Sanders now has more emotional words, and his 3rd highest emotion is now fear. Trumps and Sanders levels of positivity have dropped slightly, Trump now has his top three categories being trust, anger and anticipation.
The latest analysis shows more striking changes:
Both Clinton and Trump are now over 50% negative, with a radical change in Clintons top three emotions, these are now fear, anger and sadness. Trump has maintained a level of trust, with anger and fear coming 2nd and 3rd. It’s notable he has the highest level of disgust too amongst the four. Cruz has retained a positive tone with trust, anticipation and joy as his top three.
In the general media there is a perceived negative shift in the messages of Clinton and Trump which is reflected in the last analysis. The change in the level of tweeting is curious, but Cruz seems to tweet the most consistently in terms of volume and emotion.