One of the main questions that my group is considering basing our project on is: how often do presidents and opposing candidates break or keep their promises while in office or running for office? The idea of text mining is to thoroughly read different articles or other forms of written research and to find patterns throughout the research. These patterns consist of repeating statements or words that a person, in this president or opposing candidate), would say. This is a very beneficial way of doing our research because when a candidate is running for president or any type of office they usually use specific phrases to get the public’s attention and they constantly repeat these phrases whenever they are in public.
Like, my group member Tatsiana stated in her post, we attempt to compare what the president did during his term and what he said when he was campaigning. Unfortunatly the class is only until december, so we will not be able to do the project for the entire 4 year term of the president for this current election, but hopefully we will get an idea of what he will do up until the due date of this proejct. Along with this current election, we will also look at past presidencies and make the same coomparison. It is important that I say this becase both professors use this current election as a topic for postings and for topics of discussion in class, so it would only seem appropriate to integrate this election into our project.
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.
As Ted Underwood mentioned in the reading, some of the biggest obstacles around text mining is not only finding the data needed, but finding the skills to collect the correct data.
A reason being that our topic revolves around social media, which can be traced back not just from MySpace, but to early social networking services such as email, chat services and other early internet social structures. Also, as modern history goes, text mining can be easier as we will have more resources as sites, blogs and social applications become more accessible and popular.
After our group uncovers more secondary documents, as we feed them into a Wordle-like application we can see common themes such as undecided, voting, and different kind of feelings that stem from being a first-time voter. These similarities can help us focus on what aspect of the sources we should focus our attention towards, and can help us specify our final historical question.
In the case of secondary sources, my group may find itself in the same predicament the Underwood found himself in his own research.
However, Many of our sources with social media can be a primary source – with interviews, blogs to mine through, and various social networks to comb through by means of twitter hashtags, trending topics, and blogging categories.
One of the potential questions our group is considering to research is “How common is it for a president to break his promises made during the presidential campaign?” In order to answer this question and draw the parallels between current and historian elections, we would have to process quite large amount of text and find just the information that we need to prove our historian question. Text mining will be the essential tool in our analyses.
We will use lexical analyses that are based on searching of the key words in candidates’ speeches to find out the major promises that they made during their presidential campaign. Also, we will look for frequency of their promises – that is how often in their debates, interviews, speeches and other public appearances do they repeat these promises. Sometimes we may identify a certain patterns in their speeches that are related to their promises.
Then, we are going to compare the information that we gathered about campaign promises with the real actions these candidates made once they are elected to the presidential office. By doing this, our goal is to find out if it is common in politics for presidential candidates to make false promises to the voters, and if the voters can trust these candidates.
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.
Our group can use text mining to answer the historical question that the group has proposed about if and how the outcome of presidential debates determined who won the election. Text mining would allow us to see if there were key words or phrases used by candidates during the debates that proved to have a positive or negative effect on voters, and as result, attracted voters or deterred them away. Another way text mining will be beneficial in our project is to determine if other aspects apart from analytics played a role in deciding the outcome of elections based on a candidate’s performance during the debates. During debates, candidates present various types of data to present their case to voters: statistical data, such as their previous track record while serving in their current governmental post; and conditional data, such as what they expect to accomplish if they are chosen as president. Because debating not only deals with factual data presented by the candidates but also the manner in which the candidates convey the data, such as their behavioral disposition, body language, tone of voice, eye contact, etc., data mining will help capture the effects of these different factors and what role they played in steering the outcome of the election. However, we keep in mind that our analysis is on the premise that the election process is very complex and trying to keep all variables stable poses multifaceted challenges.
Recent Comments