Predicting Brexit: Classifying Agreement is Better than Sentiment and Pollsters

On June 23rd 2016, UK held the referendum which ratified the exit from the EU. While most of the traditional pollsters failed to forecast the final vote, there were online systems that hit the result with high accuracy using opinion mining techniques and big data. Starting one month before, we collected and monitored millions of posts about the referendum from social media conversations, and exploited Natural Language Processing techniques to predict the referendum outcome. In this paper we discuss the methods used by traditional pollsters and compare it to the predictions based on different opinion mining techniques. We find that opinion mining based on agreement/disagreement classification works better than opinion mining based on polarity classification in the forecast of the referendum outcome.

[1]  Isabell M. Welpe,et al.  Election Forecasts with Twitter - How 140 Characters Reflect the Political Landscape , 2011 .

[2]  Ellen M. Hufnagel,et al.  User Response Data: The Potential for Errors and Biases , 1994, Inf. Syst. Res..

[3]  S. Sathiya Keerthi,et al.  Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Namita Mittal,et al.  Concept-Level Sentiment Analysis with Dependency-Based Semantic Parsing: A Novel Approach , 2015, Cognitive Computation.

[5]  Erik Cambria,et al.  SenticNet 2: A Semantic and Affective Resource for Opinion Mining and Sentiment Analysis , 2012, FLAIRS.

[6]  Desheng Dash Wu,et al.  Using text mining and sentiment analysis for online forums hotspot detection and forecast , 2010, Decis. Support Syst..

[7]  Rachel Gibson,et al.  140 Characters to Victory?: Using Twitter to Predict the UK 2015 General Election , 2015, ArXiv.

[8]  Brendan T. O'Connor,et al.  From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series , 2010, ICWSM.

[9]  Raimundo Santos Moura,et al.  Using Stylometric Features for Sentiment Classification , 2015, CICLing.

[10]  Yongzheng Zhang,et al.  Recommending branded products from social media , 2013, RecSys.

[11]  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.

[12]  Fabio Celli,et al.  CorEA: Italian News Corpus with Emotions and Agreement , 2014 .

[13]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[14]  Bo Pang,et al.  A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts , 2004, ACL.

[15]  Pablo Barberá,et al.  Understanding the Political Representativeness of Twitter Users , 2015 .

[16]  Claire Cardie,et al.  Improving Agreement and Disagreement Identification in Online Discussions with A Socially-Tuned Sentiment Lexicon , 2014, WASSA@ACL.

[17]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..