{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T14:43:15Z","timestamp":1773067395553,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,23]],"date-time":"2021-10-23T00:00:00Z","timestamp":1634947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,23]],"date-time":"2021-10-23T00:00:00Z","timestamp":1634947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Special Fund for Fundamental Scientific Research of the Beijing Colleges in CUEB"},{"name":"HUMANE-AI-NET","award":["952026"],"award-info":[{"award-number":["952026"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In the past decade we have witnessed the failure of traditional polls in predicting presidential election outcomes across the world. To understand the reasons behind these failures we analyze the raw data of a trusted pollster which failed to predict, along with the rest of the pollsters, the surprising 2019 presidential election in Argentina. Analysis of the raw and re-weighted data from longitudinal surveys performed before and after the elections reveals clear biases related to mis-representation of the population and, most importantly, to social-desirability biases, i.e., the tendency of respondents to hide their intention to vote for controversial candidates. We propose an opinion tracking method based on machine learning models and big-data analytics from social networks that overcomes the limits of traditional polls. This method includes three prediction models based on the loyalty classes of users to candidates, homophily measures and re-weighting scenarios. The model achieves accurate results in the 2019 Argentina elections predicting the overwhelming victory of the candidate Alberto Fern\u00e1ndez over the incumbent\u00a0president Mauricio Macri, while none of the traditional pollsters was able to predict the large\u00a0gap between them. Beyond predicting political elections, the framework we propose is more general and can be used to discover trends in society, for instance, what people think about economics, education or climate change.<\/jats:p>","DOI":"10.1186\/s40537-021-00525-8","type":"journal-article","created":{"date-parts":[[2021,10,23]],"date-time":"2021-10-23T22:02:25Z","timestamp":1635026545000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Why polls fail to predict elections"],"prefix":"10.1186","volume":"8","author":[{"given":"Zhenkun","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Matteo","family":"Serafino","sequence":"additional","affiliation":[]},{"given":"Luciano","family":"Cohan","sequence":"additional","affiliation":[]},{"given":"Guido","family":"Caldarelli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6474-1324","authenticated-orcid":false,"given":"Hern\u00e1n A.","family":"Makse","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,23]]},"reference":[{"key":"525_CR1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199747047.001.0001","volume-title":"The science of web surveys","author":"R Tourangeau","year":"2013","unstructured":"Tourangeau R, Conrad FG, Couper MP. The science of web surveys. New York: Oxford University Press; 2013."},{"issue":"1","key":"525_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/poq\/nfx047","volume":"82","author":"C Kennedy","year":"2018","unstructured":"Kennedy C, Blumenthal M, Clement S, Clinton JD, Durand C, Franklin C, McGeeney K, Miringoff L, Olson K, Rivers D, et al. An evaluation of the 2016 election polls in the United States. Public Opin Q. 2018;82(1):1\u201333.","journal-title":"Public Opin Q"},{"issue":"1","key":"525_CR3","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1017\/S0008423919000787","volume":"53","author":"C Durand","year":"2020","unstructured":"Durand C, Blais A. Quebec 2018: a failure of the polls? Can J Polit Sci\/Revue Canadienne de Science Politique. 2020;53(1):133\u201350.","journal-title":"Can J Polit Sci\/Revue Canadienne de Science Politique"},{"key":"525_CR4","unstructured":"Duncan P, The Guardian. How the pollsters got it wrong on the EU referendum. 2016. https:\/\/www.theguardian.com\/politics\/2016\/jun\/24\/how-eu-referendum-pollsters-wrong-opinion-predict-close. Accessed 14 Oct 2021."},{"key":"525_CR5","unstructured":"Cohn N. The Upshot, New York Times. Why Polls Have Been Wrong Recently. 2016. https:\/\/www.nytimes.com\/2016\/01\/08\/upshot\/why-polls-have-been-wrong-recently.html. Accessed 14 Oct 2021."},{"key":"525_CR6","unstructured":"Jacobs J, House B. Trump says he expected to lose election because of poll results. Boomberg Politics;2016."},{"key":"525_CR7","unstructured":"Kennedy C, Hartig H. Response rates in telephone surveys have resumed their decline. Pew Research Center ;2019."},{"key":"525_CR8","first-page":"4740","volume":"1","author":"MP Battaglia","year":"2004","unstructured":"Battaglia MP, Izrael D, Hoaglin DC, Frankel MR. Tips and tricks for raking survey data (aka sample balancing). Abt Assoc. 2004;1:4740\u20134.","journal-title":"Abt Assoc"},{"key":"525_CR9","unstructured":"Izrael D, Hoaglin DC, Battaglia MP. A sas macro for balancing a weighted sample. In: Proceedings of the Twenty-fifth Annual SAS Users Group International Conference, pp. 9\u201312 ;2000. Citeseer."},{"key":"525_CR10","unstructured":"Leonhardt D. New York Times. \u2018A Black Eye\u2019: why political polling missed the mark. Again. 2020. https:\/\/www.nytimes.com\/2020\/11\/12\/us\/politics\/election-polls-trump-biden.html. Accessed 14 Oct 2021."},{"issue":"4","key":"525_CR11","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1177\/0002764210381713","volume":"54","author":"JG Payne","year":"2010","unstructured":"Payne JG. The Bradley effect: mediated reality of race and politics in the 2008 US presidential election. Am Behav Sci. 2010;54(4):417\u201335.","journal-title":"Am Behav Sci"},{"issue":"4","key":"525_CR12","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1007\/s11135-011-9640-9","volume":"47","author":"I Krumpal","year":"2013","unstructured":"Krumpal I. Determinants of social desirability bias in sensitive surveys: a literature review. Qual Quant. 2013;47(4):2025\u201347.","journal-title":"Qual Quant"},{"issue":"3","key":"525_CR13","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/s40092-017-0238-2","volume":"14","author":"M Zolghadr","year":"2018","unstructured":"Zolghadr M, Niaki SAA, Niaki S. Modeling and forecasting us presidential election using learning algorithms. J Ind Eng Int. 2018;14(3):491\u2013500.","journal-title":"J Ind Eng Int"},{"key":"525_CR14","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.knosys.2015.06.015","volume":"89","author":"K Ravi","year":"2015","unstructured":"Ravi K, Ravi V. A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowl Based Systems. 2015;89:14\u201346.","journal-title":"Knowl Based Systems"},{"issue":"3","key":"525_CR15","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1080\/01292986.2018.1453849","volume":"29","author":"K Jaidka","year":"2019","unstructured":"Jaidka K, Ahmed S, Skoric M, Hilbert M. Predicting elections from social media: a three-country, three-method comparative study. Asian J Commun. 2019;29(3):252\u201373.","journal-title":"Asian J Commun"},{"issue":"1","key":"525_CR16","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1080\/19331681.2015.1132401","volume":"13","author":"A Jungherr","year":"2016","unstructured":"Jungherr A. Twitter use in election campaigns: a systematic literature review. J Inf Technol Polit. 2016;13(1):72\u201391.","journal-title":"J Inf Technol Polit"},{"issue":"1","key":"525_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-26951-y","volume":"8","author":"A Bovet","year":"2018","unstructured":"Bovet A, Morone F, Makse HA. Validation of twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump. Sci Rep. 2018;8(1):1\u201316.","journal-title":"Sci Rep"},{"issue":"1","key":"525_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07761-2","volume":"10","author":"A Bovet","year":"2019","unstructured":"Bovet A, Makse HA. Influence of fake news in twitter during the 2016 US presidential election. Nat Commun. 2019;10(1):1\u201314.","journal-title":"Nat Commun"},{"key":"525_CR19","doi-asserted-by":"crossref","unstructured":"Papakyriakopoulos O, Hegelich S, Shahrezaye M, Serrano JCM. Social media and microtargeting: political data processing and the consequences for Germany. Big Data Soc. 2018;5(2).","DOI":"10.1177\/2053951718811844"},{"key":"525_CR20","unstructured":"Tumasjan A, Sprenger T, Sandner P, Welpe I. Predicting elections with twitter: What 140 characters reveal about political sentiment. In: Proceedings of the International AAAI Conference on Web and Social Media, 2010;vol. 4."},{"issue":"2","key":"525_CR21","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1177\/0894439311404119","volume":"30","author":"A Jungherr","year":"2012","unstructured":"Jungherr A, J\u00fcrgens P, Schoen H. Why the pirate party won the German election of 2009 or the trouble with predictions: a response to Tumasjan, A., Sprenger, TO, Sander, PG, & Welpe, IM \u201cPredicting elections with twitter: what 140 characters reveal about political sentiment\u201d. Soc Sci Comput Rev. 2012;30(2):229\u201334.","journal-title":"Soc Sci Comput Rev"},{"key":"525_CR22","doi-asserted-by":"crossref","unstructured":"Gaurav M, Srivastava A, Kumar A, Miller S. Leveraging candidate popularity on twitter to predict election outcome. In: Proceedings of the 7th workshop on social network mining and analysis, 2013;1\u20138.","DOI":"10.1145\/2501025.2501038"},{"key":"525_CR23","unstructured":"Lui C, Metaxas PT, Mustafaraj E. On the predictability of the US elections through search volume activity. http:\/\/repository.wellesley.edu\/scholarship\/23\/. Accessed 14 Oct 2021."},{"key":"525_CR24","unstructured":"Bermingham A, Smeaton A. On using twitter to monitor political sentiment and predict election results. In: Proceedings of the workshop on sentiment analysis where AI meets psychology (SAAIP 2011), 2011;2\u201310."},{"issue":"2","key":"525_CR25","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1177\/1461444813480466","volume":"16","author":"A Ceron","year":"2014","unstructured":"Ceron A, Curini L, Iacus SM, Porro G. Every tweet counts? how sentiment analysis of social media can improve our knowledge of citizens\u2019 political preferences with an application to Italy and France. New Media Soc. 2014;16(2):340\u201358.","journal-title":"New Media Soc"},{"issue":"5","key":"525_CR26","doi-asserted-by":"publisher","first-page":"95809","DOI":"10.1371\/journal.pone.0095809","volume":"9","author":"G Caldarelli","year":"2014","unstructured":"Caldarelli G, Chessa A, Pammolli F, Pompa G, Puliga M, Riccaboni M, Riotta G. A multi-level geographical study of Italian political elections from twitter data. PloS One. 2014;9(5):95809.","journal-title":"PloS One"},{"key":"525_CR27","doi-asserted-by":"crossref","unstructured":"Singh P, Sawhney RS, Kahlon KS. Forecasting the 2016 us presidential elections using sentiment analysis. In: Conference on e-Business, e-Services and e-Society, 2017; 412\u2013423 . Springer.","DOI":"10.1007\/978-3-319-68557-1_36"},{"key":"525_CR28","doi-asserted-by":"crossref","unstructured":"Xia E, Yue H, Liu H. Tweet sentiment analysis of the 2020 US presidential election. In: Companion Proceedings of the Web Conference 2021, 2021;367\u2013371.","DOI":"10.1145\/3442442.3452322"},{"issue":"2","key":"525_CR29","doi-asserted-by":"publisher","first-page":"101444","DOI":"10.1016\/j.giq.2019.101444","volume":"37","author":"P Singh","year":"2020","unstructured":"Singh P, Dwivedi YK, Kahlon KS, Pathania A, Sawhney RS. Can twitter analytics predict election outcome? an insight from 2017 Punjab assembly elections. Gov Inf Q. 2020;37(2):101444.","journal-title":"Gov Inf Q"},{"issue":"1","key":"525_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-018-0164-1","volume":"5","author":"W Budiharto","year":"2018","unstructured":"Budiharto W, Meiliana M. Prediction and analysis of Indonesia presidential election from twitter using sentiment analysis. J Big Data. 2018;5(1):1\u201310.","journal-title":"J Big Data"},{"key":"525_CR31","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199206650.001.0001","volume-title":"Networks: an introduction","author":"M Newman","year":"2010","unstructured":"Newman M. Networks: an introduction. New York: Oxford University Press; 2010."},{"issue":"4","key":"525_CR32","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1016\/j.jnca.2011.06.001","volume":"35","author":"A Cuzzocrea","year":"2012","unstructured":"Cuzzocrea A, Papadimitriou A, Katsaros D, Manolopoulos Y. Edge betweenness centrality: a novel algorithm for qos-based topology control over wireless sensor networks. J Netw Comput Appl. 2012;35(4):1210\u20137.","journal-title":"J Netw Comput Appl"},{"issue":"4","key":"525_CR33","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1080\/15377857.2014.959686","volume":"15","author":"L Bode","year":"2016","unstructured":"Bode L, Dalrymple KE. Politics in 140 characters or less: campaign communication, network interaction, and political participation on twitter. J Polit Market. 2016;15(4):311\u201332.","journal-title":"J Polit Market"},{"key":"525_CR34","unstructured":"Paladini E. Encuestadoras bajo fuego: por qu\u00e9 erraron en las PASO y qu\u00e9 dicen para octubre 2019. https:\/\/www.clarin.com\/politica\/encuestadoras-fuego-erraron-paso-dicen-octubre_0_T72H9hdl.html. Accessed 14 Oct 2021."},{"key":"525_CR35","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1126\/science.355.6324.468","volume":"355","author":"BR Jasny","year":"2017","unstructured":"Jasny BR, Stone R. Prediction and its limits. Science. 2017;355:468\u20139.","journal-title":"Science"},{"key":"525_CR36","unstructured":"Wikipedia. https:\/\/es.wikipedia.org\/wiki\/Anexo:Encuestas_de_intencion_de_voto_para_las_elecciones_presidenciales_de_Argentina_de_2019. Accessed 14 Oct 2021."},{"key":"525_CR37","unstructured":"Bonelli M. https:\/\/www.clarin.com\/opinion\/intrigas-casa-rosada-pases-factura-city-lunes-negro_0_jnggAIsh5.html. Accessed 14 Oct 2021."},{"key":"525_CR38","unstructured":"Levy R. Wall Street Journal. 2019. https:\/\/www.wsj.com\/articles\/hedge-fund-loses-1-billion-in-one-month-on-argentina-bet-11567696547. Accessed 14 Oct 2021."},{"key":"525_CR39","volume-title":"Foundations of statistical natural language processing","author":"C Manning","year":"1999","unstructured":"Manning C, Schutze H. Foundations of statistical natural language processing. MA, New York: Cambridge; 1999."},{"key":"525_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-5209-5","volume-title":"Deep learning in natural language processing","author":"L Deng","year":"2018","unstructured":"Deng L, Liu Y. Deep learning in natural language processing. Cham, Switzerland: Springer; 2018."},{"issue":"4","key":"525_CR41","doi-asserted-by":"publisher","first-page":"046108","DOI":"10.1103\/PhysRevE.84.046108","volume":"84","author":"J Martinez-Romo","year":"2011","unstructured":"Martinez-Romo J, Araujo L, Borge-Holthoefer J, Arenas A, Capit\u00e1n JA, Cuesta JA. Disentangling categorical relationships through a graph of co-occurrences. Phys Rev E. 2011;84(4):046108.","journal-title":"Phys Rev E"},{"issue":"1","key":"525_CR42","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0894439314521983","volume":"33","author":"A Ceron","year":"2015","unstructured":"Ceron A, Curini L, Iacus SM. Using sentiment analysis to monitor electoral campaigns: method matters-evidence from the United States and Italy. Soc Sci Comput Rev. 2015;33(1):3\u201320.","journal-title":"Soc Sci Comput Rev"},{"key":"525_CR43","doi-asserted-by":"crossref","unstructured":"An J, Weber I. #greysanatomy vs #yankees: Demographics and hashtag use on Twitter. In: Proceedings of the International AAAI Conference on Web and Social Media; 2016. p. 10.","DOI":"10.1609\/icwsm.v10i1.14767"},{"key":"525_CR44","doi-asserted-by":"crossref","unstructured":"Vikatos P, Messias J, Miranda M, Benevenuto F. Linguistic diversities of demographic groups in Twitter. In: Proceedings of the 28th ACM Conference on Hypertext and Social Media; 2017. p. 275\u201384.","DOI":"10.1145\/3078714.3078742"},{"key":"525_CR45","unstructured":"New York Times National Polling Average. The Upshot. http:\/\/www.nytimes.com\/interactive\/2016\/us\/elections\/polls.html. Accessed 14 Oct 2021."},{"key":"525_CR46","unstructured":"SEIDO - Special Report: Lie to Me. https:\/\/us3.campaign-archive.com\/?e=&u=e02ede36ce39515be5fb17728&id=3bf5cf2e90. Accessed 14 Oct 2021."}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-021-00525-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-021-00525-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-021-00525-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T15:04:55Z","timestamp":1673622295000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-021-00525-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,23]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["525"],"URL":"https:\/\/doi.org\/10.1186\/s40537-021-00525-8","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,23]]},"assertion":[{"value":"8 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"137"}}