digging for whats important

Throughout the process of gathering information and data to help support our argument concerning debates on voter behavior, text mining will be pertinent.  Going through large amounts of numbers and words to grab and portray what is important and what is essential for the project is the basis of text mining.  Many broadcast companies now have a system which they give a room full of undecided voters a device to grasp their emotions and reactions to what the candidates are saying.  Word by word, topic by topic, we can understand what ideas presented affect this group of people.  It is either positive, negative or no response- such as if the moderator is speaking.  Digging through these numbers could help us convey our argument.  Making a correlation between what a candidate says, to how people react, to then the numbers at the polls could be attained by text mining. It would be important to understand how many people are actually studied with these devices and how much it actually represents the general public or those who are all undecided.  I believe these studies have large amounts of numbers and information that can help us make direct correlations to election day results. I am a little unsure as to how we actually will attain these numbers and what programs are used to get the pertinent data.