US Presidential Election 2012 Prediction using Census Corrected Twitter Model

Abstract US Presidential Election 2012 has been a very tight race between the two key candidates. There were intense battle between the two key candidates. The election reflects the sentiment of the electorate towards the achievements of the incumbent President Obama. The campaign lasted several months and the effects can be felt in the internet and twitter. The presidential debates injected new vigor in the challenger's campaign and successfully captured the electorate of several states posing a threat to the incumbent's position. Much of the sentiment in the election has been captured in the online discussions. In this paper, we will be using the original model described in Choy et. al. (2011) using twitter data to forecast the next US president. Introduction Social media has been widely used by politicians to increase the reach of their campaigns. The campaign of President Obama in 2008 demonstrated the power and reach of social media and how it can be used to change the political landscape. Social media platforms have been touted as the leading platform to engage voters. Political analysts (Stirland, 2008; Pasek, 2006; Xenos, 2007) attributed the success to the active and effective use of social media platforms to engage voters notably the younger generations usually ignored or given less importance (Pasek, 2006) by veteran politicians. The use of social media also helped to reach small population such as the Hispanics and activate support for the candidates. The poor management of social media platforms and absymal out reaches by McCain and Palin improved Obama's overall advantage in attracting voters (Stirland, 2008) and encouraging their turnout. Twitter has become a popular tool of choice for politicians to spread influence. Twitter was developed as a micro-blogging tool where all the status updates as well as the opinions written can be searched and extracted using the twitter search API (Twitter, 2011). Search capabilities allow almost real life time viewing of information posted online by various users. Political associations as well as various activitist groups have successfully used it to voice their opinions, political positions as well as gathering supports from the online audiences. Every campaign has an online presence and the research focus on the formulation of these successful online campaigns. Campaigners are on a constant lookout for new social media channels to garner supporters and drive voter shares. There are many analysts and skeptics who believe that twitter is not very useful (Pearanalytics, 2009; Gayo-Avello, 2012), others have lauded the immense potential of twitter (Skemp ,2009). There are three major objectives to be achieved using twitter information. The first aim is to assess the validity of the framework proposed in Choy et. al. (2011) to predict the new President. The second aim is to assess the methodology's power to calculate and predict state level electorate results. Finally, we will also like to evaluate the impact of twitter on the greater internet as a whole.

[1]  Mary Ting.  Big Things Come in Small Packages , 2012 .

[2]  Isabell M. Welpe,et al.  Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment , 2010, ICWSM.

[3]  Michael S. Lewis-Beck,et al.  The Job of President and the Jobs Model Forecast: Obama for '08? , 2008, PS: Political Science & Politics.

[4]  Kate Kenski,et al.  America's Youth and Community Engagement , 2006, Commun. Res..

[5]  Jon A. Krosnick,et al.  The Impact of Anti-Black Racism on Approval of Barack Obama's Job Performance and on Voting in the 2012 Presidential Election , 2012 .

[6]  A. Pole,et al.  What do bloggers do: an average day on an average political blog , 2007 .

[7]  Cass R. Sunstein,et al.  Neither Hayek nor Habermas , 2007 .

[8]  Daniel W. Drezner,et al.  Introduction: Blogs, politics and power: a special issue of Public Choice , 2007 .

[9]  Christine B. Williams,et al.  What is a Social Network Worth? Facebook and Vote Share in the 2008 Presidential Primaries , 2008 .

[10]  Bernard J. Jansen,et al.  Twitter power: Tweets as electronic word of mouth , 2009, J. Assoc. Inf. Sci. Technol..

[11]  Panagiotis Takis Metaxas,et al.  Vocal Minority Versus Silent Majority: Discovering the Opionions of the Long Tail , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[12]  H. Jansen,et al.  Political Blogs and Blogrolls in Canada , 2009 .

[13]  Spencer Piston,et al.  How Explicit Racial Prejudice Hurt Obama in the 2008 Election , 2010 .

[14]  Krishna P. Gummadi,et al.  Measuring User Influence in Twitter: The Million Follower Fallacy , 2010, ICWSM.

[15]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[16]  Fang Wu,et al.  Social Networks that Matter: Twitter Under the Microscope , 2008, First Monday.

[17]  Simon Jackman,et al.  How Does Obama Match-Up? Counterfactuals & the Role of Obama's Race in 2008 , 2011 .

[18]  B. Highton,et al.  Prejudice Rivals Partisanship and Ideology When Explaining the 2008 Presidential Vote across the States , 2011, PS: Political Science & Politics.

[19]  Murphy Choy,et al.  A sentiment analysis of Singapore Presidential Election 2011 using Twitter data with census correction , 2011, ArXiv.

[20]  Daniel W. Drezner,et al.  The power and politics of blogs , 2007 .

[21]  J. Scott Armstrong,et al.  Predicting Elections from Biographical Information about Candidates , 2009 .

[22]  Jacob Ratkiewicz,et al.  Political Polarization on Twitter , 2011, ICWSM.

[23]  Ray C. Fair,et al.  Econometrics and Presidential Elections , 1996 .

[24]  H. Jansen,et al.  Pundits, Ideologues, and the Ranters: The British Columbia Election Online , 2006 .

[25]  Daniel Gayo-Avello,et al.  "I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper" - A Balanced Survey on Election Prediction using Twitter Data , 2012, ArXiv.

[26]  Allan J. Lichtman,et al.  The thirteen keys to the presidency , 1988 .

[27]  Michael A. Xenos,et al.  The Disconnection In Online Politics: the youth political web sphere and US election sites, 2002–2004 , 2007 .

[28]  Vincent L. Hutchings.  Change or More of The Same? Evaluating Racial Attitudes in the Obama Era , 2009 .

[29]  Susan C. Herring,et al.  Beyond Microblogging: Conversation and Collaboration via Twitter , 2009, 2009 42nd Hawaii International Conference on System Sciences.

[30]  Peter A. Hall.  This year’s American Presidential election is a contestbetween those who advocate the politics of “everyone forthemselves” and those of intergenerational fairness: European social democrats should watch closely , 2012 .

[31]  Alexander Richter,et al.  Adopting Social Software to the Intranet: A Case Study on Enterprise Microblogging , 2009 .

[32]  Timothy W. Finin,et al.  Why we twitter: understanding microblogging usage and communities , 2007, WebKDD/SNA-KDD '07.

[33]  Allan J. Lichtman.  The Keys to the White House , 1996 .

[34]  Jacob Ratkiewicz,et al.  Detecting and Tracking Political Abuse in Social Media , 2011, ICWSM.

[35]  Panagiotis Takis Metaxas,et al.  What Edited Retweets Reveal about Online Political Discourse , 2011, Analyzing Microtext.

[36]  Jon A. Krosnick,et al.  Determinants of Turnout and Candidate Choice in the 2008 U.S. Presidential Election Illuminating the Impact of Racial Prejudice and Other Considerations , 2009 .

[37]  Panagiotis Takis Metaxas,et al.  How (Not) to Predict Elections , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[38]  Panagiotis Takis Metaxas,et al.  Limits of Electoral Predictions Using Twitter , 2011, ICWSM.