User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump

Primary tabs

download
  • Open access
  • PDF
  • 5.84 M
Bovet, Alexandre [UCL] Morone, Flaviano Makse, Hernán A.

Measuring and forecasting opinion trends from real-time social media is a long-standing goal of big-data analytics. Despite its importance, there has been no conclusive scientific evidence so far that social media activity can capture the opinion of the general population. Here we develop a method to infer the opinion of Twitter users regarding the candidates of the 2016 US Presidential Election by using a combination of statistical physics of complex networks and machine learning based on hashtags co-occurrence to develop an in-domain training set approaching 1 million tweets. We investigate the social networks formed by the interactions among millions of Twitter users and infer the support of each user to the presidential candidates. The resulting Twitter trends follow the New York Times National Polling Average, which represents an aggregate of hundreds of independent traditional polls, with remarkable accuracy. Moreover, the Twitter opinion trend precedes the aggregated NYT polls by 10 days, showing that Twitter can be an early signal of global opinion trends. Our analytics unleash the power of Twitter to uncover social trends from elections, brands to political movements, and at a fraction of the cost of national polls.

Document type Article de périodique (Journal article) – Article de recherche
Access type Accès libre
Publication date 2018
Language Anglais
Journal information "Scientific Reports" - Vol. 8, no.1 (2018)
Peer reviewed yes
Publisher Springer Nature
e-issn 2045-2322
Publication status Publié
Affiliation UCL - SST/ICTM/INMA - Pôle en ingénierie mathématique
Links
  1. Mislove, A., Lehmann, S., Ahn, Y.-Y., Onnela, J.-P. & Rosenquist, J. N. Pulse of the nation: US mood throughout the day inferred from Twitter http://www.ccs.neu.edu/home/amislove/twittermood/ (2010).
  2. Hannak, A. et al. Tweetin’ in the rain: exploring societal-scale effects of weather on mood. In Proc. 6th Int. AAAI Conf. Weblogs Soc. Media, 479–482 (Dublin, Ireland, 2012).
  3. Pak, A. & Paroubek, P. Twitter as a corpus for sentiment analysis and opinion mining. In Proc. Seventh Int. Conf. Lang. Resour. Eval., pp. 19–21 (European Language Resources Association (ELRA), Valletta, Malta, 2010).
  4. Quattrociocchi Walter, Caldarelli Guido, Scala Antonio, Opinion dynamics on interacting networks: media competition and social influence, 10.1038/srep04938
  5. Liu Yang, Huang Xiangji, An Aijun, Yu Xiaohui, ARSA : a sentiment-aware model for predicting sales performance using blogs, 10.1145/1277741.1277845
  6. Bollen Johan, Mao Huina, Zeng Xiaojun, Twitter mood predicts the stock market, 10.1016/j.jocs.2010.12.007
  7. Zheludev Ilya, Smith Robert, Aste Tomaso, When Can Social Media Lead Financial Markets?, 10.1038/srep04213
  8. Ranco Gabriele, Aleksovski Darko, Caldarelli Guido, Grčar Miha, Mozetič Igor, The Effects of Twitter Sentiment on Stock Price Returns, 10.1371/journal.pone.0138441
  9. CURME CHESTER, STANLEY H. EUGENE, VODENSKA IRENA, COUPLED NETWORK APPROACH TO PREDICTABILITY OF FINANCIAL MARKET RETURNS AND NEWS SENTIMENTS, 10.1142/s0219024915500430
  10. O’Connor, B., Balasubramanyan, R., Routledge, B. R. & Smith, N. a. From tweets to polls: Linking text sentiment to public opinion time series. 122–129, DOI:citeulike-article-id:7044833 (2010).
  11. Tumasjan Andranik, Sprenger Timm O., Sandner Philipp G., Welpe Isabell M., Election Forecasts With Twitter : How 140 Characters Reflect the Political Landscape, 10.1177/0894439310386557
  12. Shi, L., Agarwal, N., Agrawal, A., Garg, R. & Spoelstra, J. Predicting US primary elections with Twitter. In Proc. Work. Soc. Netw. Soc. Media Anal., 1–8 (Lake Tahoe, Nevada, 2012).
  13. Marchetti-Bowick, M. & Chambers, N. Learning for microblogs with distant supervision: political forecasting with Twitter. In Proc. 13th Conf. Eur. Chapter Assosciation Comput. Linguist. 603–612 (2012).
  14. Borondo J., Morales A. J., Losada J. C., Benito R. M., Characterizing and modeling an electoral campaign in the context of Twitter: 2011 Spanish Presidential election as a case study, 10.1063/1.4729139
  15. Park, S., Ko, M., Lee, J. & Song, J. Agenda diversity in social media discourse: a study of the 2012 korean general election. In Proc. 7th Int. Conf. Web Soc. Media 486–495 (2012).
  16. Contractor Danish, Faruquie Tanveer Afzal, Understanding election candidate approval ratings using social media data, 10.1145/2487788.2487883
  17. Thapen, N. A. & Ghanem, M. M. Towards passive political opinion polling using twitter. In CEUR Workshop Proc., vol. 1110, 19–34 (2013).
  18. Hoang Tuan-Anh, Cohen William W., Lim Ee-Peng, Pierce Doug, Redlawsk David P., Politics, sharing and emotion in microblogs, 10.1145/2492517.2492554
  19. Fink Clay, Bos Nathan, Perrone Alexander, Liu Edwina, Kopecky Jonathon, Twitter, Public Opinion, and the 2011 Nigerian Presidential Election, 10.1109/socialcom.2013.50
  20. Gayo-Avello Daniel, A Meta-Analysis of State-of-the-Art Electoral Prediction From Twitter Data, 10.1177/0894439313493979
  21. Caldarelli Guido, Chessa Alessandro, Pammolli Fabio, Pompa Gabriele, Puliga Michelangelo, Riccaboni Massimo, Riotta Gianni, A Multi-Level Geographical Study of Italian Political Elections from Twitter Data, 10.1371/journal.pone.0095809
  22. Borge-Holthoefer Javier, Magdy Walid, Darwish Kareem, Weber Ingmar, Content and Network Dynamics Behind Egyptian Political Polarization on Twitter, 10.1145/2675133.2675163
  23. Tsakalidis Adam, Papadopoulos Symeon, Cristea Alexandra I., Kompatsiaris Yiannis, Predicting Elections for Multiple Countries Using Twitter and Polls, 10.1109/mis.2015.17
  24. Kagan Vadim, Stevens Andrew, Subrahmanian V.S., Using Twitter Sentiment to Forecast the 2013 Pakistani Election and the 2014 Indian Election, 10.1109/mis.2015.16
  25. Saifuddin, A., Kokil, J. & Marko, M. S. Tweets & votes - a 4 country comparison of volumetric and sentiment analysis approcahes. In Proc. 10th Int. Conf. Web Soc. Media, 507–510 (2016).
  26. Wang, Y., Li, Y. & Luo, J. Deciphering the 2016 U.S. presidential campaign in the Twitter sphere: a comparison of the trumpists and clintonists. In Proc. 10th Int. Conf. Web Soc. Media, 4 (2016).
  27. Llewellyn, C. & Cram, L. Brexit? analyzing opinion on the uk-eu referendum within Twitter. In Proc. 10th Int. Conf. Web Soc. Media, 760–761 (2016).
  28. Jungherr Andreas, Jürgens Pascal, Schoen Harald, Why the Pirate Party Won the German Election of 2009 or The Trouble With Predictions: A Response to Tumasjan, A., Sprenger, T. O., Sander, P. G., & Welpe, I. M. “Predicting Elections With Twitter: What 140 Characters Reveal About Political Sentiment”, 10.1177/0894439311404119
  29. Jungherr, A., Schoen, H., Posegga, O. & Jurgens, P. Digital trace data in the study of public opinion: an indicator of attention toward politics rather than political support. Soc. Sci. Comput. Rev. 0894439316631043 (2016).
  30. Subrahmanian V.S., Reforgiato Diego, AVA: Adjective-Verb-Adverb Combinations for Sentiment Analysis, 10.1109/mis.2008.57
  31. Montejo-Ráez Arturo, Martínez-Cámara Eugenio, Martín-Valdivia M. Teresa, Ureña-López L. Alfonso, Ranked WordNet graph for Sentiment Polarity Classification in Twitter, 10.1016/j.csl.2013.04.001
  32. Tausczik Yla R., Pennebaker James W., The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods, 10.1177/0261927x09351676
  33. González-Bailón Sandra, Paltoglou Georgios, Signals of Public Opinion in Online Communication : A Comparison of Methods and Data Sources, 10.1177/0002716215569192
  34. Ceron Andrea, Curini Luigi, Iacus Stefano M., Using Sentiment Analysis to Monitor Electoral Campaigns : Method Matters—Evidence From the United States and Italy, 10.1177/0894439314521983
  35. Beauchamp Nicholas, Predicting and Interpolating State-Level Polls Using Twitter Textual Data : PREDICTING POLLS WITH TWITTER, 10.1111/ajps.12274
  36. Sylwester Karolina, Purver Matthew, Twitter Language Use Reflects Psychological Differences between Democrats and Republicans, 10.1371/journal.pone.0137422
  37. Ceron Andrea, Curini Luigi, Iacus Stefano Maria, iSA: A fast, scalable and accurate algorithm for sentiment analysis of social media content, 10.1016/j.ins.2016.05.052
  38. Ceron, A., Curini, L. & Iacus, S. Politics and Big Data: Nowcasting and Forecasting Elections with Social Media (Taylor & Francis, 2017).
  39. Hopkins Daniel J., King Gary, A Method of Automated Nonparametric Content Analysis for Social Science, 10.1111/j.1540-5907.2009.00428.x
  40. New York Times. New York Times National Polling Average http://www.nytimes.com/interactive/2016/us/elections/polls.html [Online; accessed 24-April-2017] (2016).
  41. Ceron, A., Curini, L. & Iacus, S. Politics and Big Data: Nowcasting and Forecasting Elections with Social Media, chap. 3 (Taylor & Francis, 2017).
  42. Pei Sen, Muchnik Lev, Andrade, José S., Zheng Zhiming, Makse Hernán A., Searching for superspreaders of information in real-world social media, 10.1038/srep05547
  43. Bunde, A. & Havlin, S. Fractals and Disordered Systems (Springer Berlin Heidelberg, 2012).
  44. Bollobás, B. Random Graphs. Cambridge Studies in Advanced Mathematics (Cambridge University Press, 2001).
  45. Raghavan Usha Nandini, Albert Réka, Kumara Soundar, Near linear time algorithm to detect community structures in large-scale networks, 10.1103/physreve.76.036106
  46. Blondel Vincent D, Guillaume Jean-Loup, Lambiotte Renaud, Lefebvre Etienne, Fast unfolding of communities in large networks, 10.1088/1742-5468/2008/10/p10008
  47. Newman M. E. J., Girvan M., Finding and evaluating community structure in networks, 10.1103/physreve.69.026113
  48. Barberá Pablo, Jost John T., Nagler Jonathan, Tucker Joshua A., Bonneau Richard, Tweeting From Left to Right : Is Online Political Communication More Than an Echo Chamber?, 10.1177/0956797615594620
  49. Mills, T. Time Series Techniques for Economists (Cambridge University Press, 1991).
  50. Seabold, S. & Perktold, J. Statsmodels: Econometric and statistical modeling with python. In 9th Python in Science Conference (2010).
  51. Amador Diaz Lopez Julio Cesar, Collignon-Delmar Sofia, Benoit Kenneth, Matsuo Akitaka, Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data, 10.1515/spp-2017-0006
  52. Bohannon John, The pulse of the people, 10.1126/science.355.6324.470
  53. Jasny Barbara R., Stone Richard, Prediction and its limits, 10.1126/science.355.6324.468
  54. Wang Xiaolong, Wei Furu, Liu Xiaohua, Zhou Ming, Zhang Ming, Topic sentiment analysis in twitter : a graph-based hashtag sentiment classification approach, 10.1145/2063576.2063726
  55. Pew Research Center. Assessing the representativeness of public opinion surveys http://www.people-press.org/2012/05/15/assessing-the-representativeness-of-public-opinion-surveys. [Online; accessed 5-October-2016] (2013).
  56. Conover Michael D, Gonçalves Bruno, Flammini Alessandro, Menczer Filippo, Partisan asymmetries in online political activity, 10.1140/epjds6
  57. Pew Research Center. Social media update 2016 http://www.pewinternet.org/2016/11/11/social-media-update-2016/. [Online; accessed 7-March-2017] (2016).
  58. Joseph Kenneth, Landwehr Peter M., Carley Kathleen M., Two 1%s Don’t Make a Whole: Comparing Simultaneous Samples from Twitter’s Streaming API, Social Computing, Behavioral-Cultural Modeling and Prediction (2014) ISBN:9783319055787 p.75-83, 10.1007/978-3-319-05579-4_10
  59. Twitter Documentation. Twitter API authentication https://developer.twitter.com/en/docs/basics/authentication/guides/access-tokens [Online; accessed 26-February-2018] (2018).
  60. Twitter Documentation. Tweet object https://developer.twitter.com/en/docs/tweets/data-dictionary/overview/tweet-object [Online; accessed 26-February-2018] (2018).
  61. Varol, O., Ferrara, E., Davis, C. A., Menczer, F. & Flammini, A. Online human-bot interactions: detection, estimation, and characterization. In Proc. 11th Int. AAAI Conf. Weblogs Soc. Media 280–289 (2017).
  62. Martinez-Romo Juan, Araujo Lourdes, Borge-Holthoefer Javier, Arenas Alex, Capitán José A., Cuesta José A., Disentangling categorical relationships through a graph of co-occurrences, 10.1103/physreve.84.046108
  63. Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning, vol. 1 of Springer Series in Statistics (Springer New York, New York, NY, 2009).
  64. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Bibliographic reference Bovet, Alexandre ; Morone, Flaviano ; Makse, Hernán A.. Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. In: Scientific Reports, Vol. 8, no.1 (2018)
Permanent URL http://hdl.handle.net/2078.1/203778