Using Text Mining for Our Projects
Text mining involves a program analyzing large volumes of unstructured data for the purpose of extraction of specific words and key phrases.
Since both of our historical questions proposed so far involve social media, we will need to use as many social media websites as we can because larger amounts of data will be better for comparison and analysis.
Unlike Ted Underwood, who needed literary works for his project, we can obtain the necessary information straight from the social media websites.
As far as the necessity of learning how to program, I am not sure whether it will be necessary for our project or not. The public toolsets for text mining, given as examples on professor Underwood’s website, seem sufficient enough for the job.
Text mining will help us divide and categorize information, thereby revealing patterns.
In our case, text mining will be used to determine how the names of presidential candidates, “Presidential Election 2012,” and popular political issues, are being used by young/first time voters. This election is arguably is first to be so immersed by the social media, which makes it perfect for this project.
I am not sure if my response is adequate enough for the posted question. Perhaps if I came to class last Wednesday, it would have been better. Unfortunately, the train tracks between my house and Baruch were broken at Prospect Park station.
Very good points, Anton. Your definition of text mining is a useful one, and your references to the tools and strategies from the Ted Underwood piece are well done. I agree that text mining will be an extremely helpful tool for analyzing the role of social media in the 2012 election. Along those lines: what patterns might you look for in the data collected from social media? What particular keywords or patterns may help answer the question(s) your group is considering?