The day has come and gone on this 20th of January in 2017. Donald Trump has been sworn in as the 45th President of the United States, and like his predecessors, Trump gave an inaugural address during today's ceremony. Lots of pundits, of course, have spent today closely analyzing, scrutinizing, praising, and whatever-else-ing Trump's speech. Like everyone of these pundits, I have personal thoughts about the events that have transpired today as well, but, rather than simply contribute to the discordant cacophony of punditry a contrived opinion of my own, I'm choosing to do something more constructive (or at least less politically volatile) in an effort to offer something of novel import to discussion about President Trump's address. Rather than qualitatively sift through every word and nuance of Trump's inaugural address, I'll do something political science-y: use some textual analysis techniques to leverage quantifiable insights from Trump's speech.
The Method
To analyze Trump's address, I utilized a dictionary method of text analysis that relies on the NRC Emotion Lexicon -- a set of crowd-sourced word-emotion and word-sentiment associations. This lexicon contains word associations with eight emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and with two sentiments (positive and negative). I used R statistical software for my analysis. To offer a fuller overview of sentiment and emotion in Trump's address, I broke down his speech by sentence so that I could capture and display, in order, a timeline of variation in sentiment valence and the fluctuation of various emotions in his speech from start to finish.
Variation in Positive vs. Negative Sentiment
The below figure displays the sentiment valence (i.e., the fluctuation in positive vs. negative sentiment) in Trump's inaugural address from beginning to end.
It seems that Trump kept things mostly positive. Positive sentiment spiked to its highest level (+6) early in his address, and for the majority of his speech thereafter, spikes in positive sentiment appear to significantly outweigh the valleys of negative sentiment (which go as low as -2) that punctuate his address.
Maintaining a mostly positive message (of course positive is a relative term when it comes to politics) likely serves Trump well, as it would any incoming president. Sending positive signals to one's base can certainly win any politician political points among supporters.
Emotions in Trump's Speech
Regarding the eight emotions detectable using the NRC Emotion Lexicon, the below figure reveals some telling semantic patterns in Trump's address.
Two notable patterns stand out. Most importantly, as Trump's speech progresses an increase in anticipation is clearly present as the address approaches its end. Furthermore, both joy and trust appear in comparatively high proportions relative to other emotions; however, fear and surprise, along with anger, make punctuated appearances. The overall trend in Trump's inaugural address, therefore, seems to be one of mounting anticipation with gestures of joy and trust playing important supporting roles; but, some negative emotions (anger most tellingly, which spikes to +4 at one point) occasionally arise. Disgust and sadness also are detected, but the frequency and magnitude of their appearances are not all that substantial.
Conclusion
So, based on the numbers at least, Trump appears to have issued a relatively positive inaugural address, one that was intended to build anticipation and convey joy and trust, but which did contain some negativity as well. Of course, to better put this address in context it might be good to compare these results to an analysis of President Obama's, and other past presidents', inaugural addresses in future posts (perhaps as a part of a series...what fun!).
___________________________________________
Learn more about how I did the above analysis by checking out this project on my GitHub: Inaugural Address of Donald Trump
The Method
To analyze Trump's address, I utilized a dictionary method of text analysis that relies on the NRC Emotion Lexicon -- a set of crowd-sourced word-emotion and word-sentiment associations. This lexicon contains word associations with eight emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and with two sentiments (positive and negative). I used R statistical software for my analysis. To offer a fuller overview of sentiment and emotion in Trump's address, I broke down his speech by sentence so that I could capture and display, in order, a timeline of variation in sentiment valence and the fluctuation of various emotions in his speech from start to finish.
Variation in Positive vs. Negative Sentiment
The below figure displays the sentiment valence (i.e., the fluctuation in positive vs. negative sentiment) in Trump's inaugural address from beginning to end.
It seems that Trump kept things mostly positive. Positive sentiment spiked to its highest level (+6) early in his address, and for the majority of his speech thereafter, spikes in positive sentiment appear to significantly outweigh the valleys of negative sentiment (which go as low as -2) that punctuate his address.
Maintaining a mostly positive message (of course positive is a relative term when it comes to politics) likely serves Trump well, as it would any incoming president. Sending positive signals to one's base can certainly win any politician political points among supporters.
Emotions in Trump's Speech
Regarding the eight emotions detectable using the NRC Emotion Lexicon, the below figure reveals some telling semantic patterns in Trump's address.
Two notable patterns stand out. Most importantly, as Trump's speech progresses an increase in anticipation is clearly present as the address approaches its end. Furthermore, both joy and trust appear in comparatively high proportions relative to other emotions; however, fear and surprise, along with anger, make punctuated appearances. The overall trend in Trump's inaugural address, therefore, seems to be one of mounting anticipation with gestures of joy and trust playing important supporting roles; but, some negative emotions (anger most tellingly, which spikes to +4 at one point) occasionally arise. Disgust and sadness also are detected, but the frequency and magnitude of their appearances are not all that substantial.
Conclusion
So, based on the numbers at least, Trump appears to have issued a relatively positive inaugural address, one that was intended to build anticipation and convey joy and trust, but which did contain some negativity as well. Of course, to better put this address in context it might be good to compare these results to an analysis of President Obama's, and other past presidents', inaugural addresses in future posts (perhaps as a part of a series...what fun!).
___________________________________________
Learn more about how I did the above analysis by checking out this project on my GitHub: Inaugural Address of Donald Trump
Comments
Post a Comment