Objective: Visualize a word count of each participant in the presidential debate on September 30, 2020.
With the United States presidential election coming up, I wanted to explore and analyze the transcript of the debate this past week. First, I downloaded a transcript from rev.com as a .txt file. Then, I created 3 dictionaries in my program, one for each person: Chris Wallace, Joe Biden, and Donald Trump. I associated each word with its word count and then assigned each person a box on the canvas. I decided to omit the words [“a”, “is”, “of”, “in”, “to”, “an”, “the”, “and”, “on”, “it”, “that”, “at”] to provide a more fruitful analysis of each person’s speech. Arguably, I could have included more words to omit. However, I felt this was a good start. Words with a frequency less than 5 times were also omitted from the visualization. Each word increases in size and in brightness depending on its frequency.
I originally wanted to make my program more interactive where users can listen to the debate and see the word count live at the same time. However, since there are 3 people talking in the audio it would be hard to maintain the association of who spoke those words at any given time. I think I could try to implement this with more time and using a transcript with timestamps and p5.speech.js
Overall, I think my algorithm needs to be refined (maybe omit more words) to learn more about the significance of each person’s speech and their word counts.