Bloomberg Press Release Text Analysis

A series of 3 sketches takes a text file containing all press releases pertaining to Sandy from 10/26 – 11/4 and counts the total number of times each word occurs. A conditional statement checks and skips the count for words like AND or THE. The second sketch gets rid of all duplicate entries in the text file. The third sketch load the final data and most used words are displayed and scaled based on word count.

I had initially wanted this more interactive, you click on a certain date, and the word cloud for that day would appear above – that will be the next step.

the code

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>