{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T07:52:24Z","timestamp":1777103544559,"version":"3.51.4"},"reference-count":68,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T00:00:00Z","timestamp":1585612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["11674116"],"award-info":[{"award-number":["11674116"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In recent years, many studies have used social media data to make estimates of electoral outcomes and public opinion. This paper reports the findings from a meta-analysis examining the predictive power of social media data by focusing on various sources of data and different methods of prediction; i.e., (1) sentiment analysis, and (2) analysis of structural features. Our results, based on the data from 74 published studies, show significant variance in the accuracy of predictions, which were on average behind the established benchmarks in traditional survey research. In terms of the approaches used, the study shows that machine learning-based estimates are generally superior to those derived from pre-existing lexica, and that a combination of structural features and sentiment analyses provides the most accurate predictions. Furthermore, our study shows some differences in the predictive power of social media data across different levels of political democracy and different electoral systems. We also note that since the accuracy of election and public opinion forecasts varies depending on which statistical estimates are used, the scientific community should aim to adopt a more standardized approach to analyzing and reporting social media data-derived predictions in the future.<\/jats:p>","DOI":"10.3390\/info11040187","type":"journal-article","created":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T13:27:19Z","timestamp":1585661239000},"page":"187","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Electoral and Public Opinion Forecasts with Social Media Data: A Meta-Analysis"],"prefix":"10.3390","volume":"11","author":[{"given":"Marko M.","family":"Skoric","sequence":"first","affiliation":[{"name":"Department of Media and Communication, City University of Hong Kong, Hong Kong 999077, China"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"HKUST Business School, Hong Kong University of Science and Technology, Hong Kong 999077, China"}]},{"given":"Kokil","family":"Jaidka","sequence":"additional","affiliation":[{"name":"Department of Communications and New Media, National University of Singapore, Singapore 117416, Singapore"}]}],"member":"1968","published-online":{"date-parts":[[2020,3,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1126\/science.1197872","article-title":"Ensuring the data-rich future of the social sciences","volume":"331","author":"King","year":"2011","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1126\/science.1167742","article-title":"Life in the network: The coming age of computational social science","volume":"323","author":"Lazer","year":"2009","journal-title":"Science"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1080\/1369118X.2012.678878","article-title":"Critical questions for big data: Provocations for a cultural, technological, and scholarly phenomenon","volume":"15","author":"boyd","year":"2012","journal-title":"Inf. Commun. Soc."},{"key":"ref_4","unstructured":"Salganik, M.J. (2018). Bit by Bit: Social Research in the Digital Age, Princeton University Press."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1111\/j.1475-4932.2012.00809.x","article-title":"Predicting the present with Google Trends","volume":"88","author":"Choi","year":"2012","journal-title":"Econ. Rec."},{"key":"ref_6","unstructured":"Gold, M.K. (2011). Trending: The promises and the challenges of big social data. Debates in the Digital Humanities, The University of Minnesota Press."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.socnet.2014.01.004","article-title":"Assessing the bias in samples of large online networks","volume":"38","author":"Wang","year":"2014","journal-title":"Soc. Netw."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1177\/0894439311404119","article-title":"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. \u201cPredicting elections with Twitter: What 140 characters reveal about political sentiment.\u201d","volume":"30","author":"Jungherr","year":"2012","journal-title":"Soc. Sci. Comput. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Burgess, J., Marwick, A., and Poell, T. (2018). The Affordances of Social Media Platforms. The SAGE Handbook of Social Media, Sage Publications.","DOI":"10.4135\/9781473984066"},{"key":"ref_10","unstructured":"Ratkiewicz, J., Conover, M., Meiss, M.R., Gon\u00e7alves, B., Flammini, A., and Menczer, F. (April, January 28). Detecting and Tracking Political Abuse in Social Media. Proceedings of the 20th international conference companion on World Wide Web, Hyderabad, India."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1177\/0894439313493979","article-title":"A meta-analysis of state-of-the-art electoral prediction from Twitter data","volume":"31","year":"2013","journal-title":"Soc. Sci. Comput. Rev."},{"key":"ref_12","unstructured":"Mattelart, A., and Siegelaub., S. (1979). Public opinion does not exist. Communication and Class Strugzle, International General\/IMMRC."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1086\/266685","article-title":"Public opinion and the classical tradition","volume":"21","author":"Lazarsfeld","year":"1957","journal-title":"Public Opin. Q."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1086\/266687","article-title":"The two-step flow of communication: An up-to-date report on an hypothesis","volume":"21","author":"Katz","year":"1957","journal-title":"Public Opin. Q."},{"key":"ref_15","unstructured":"Katz, E., and Lazarsfeld, P.F. (1955). Personal Influence: The Part Played by People in the Flow of Mass Communications, Free Press."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1177\/1461444813480466","article-title":"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","volume":"16","author":"Ceron","year":"2014","journal-title":"New Media Soc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1086\/517897","article-title":"Rankings and reactivity: How public measures recreate social worlds","volume":"113","author":"Espeland","year":"2007","journal-title":"Am. J. Sociol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.2307\/2991824","article-title":"The two faces of public opinion","volume":"43","author":"Berinsky","year":"1999","journal-title":"Am. J. Political Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"542","DOI":"10.2307\/2087146","article-title":"Public opinion and public opinion polling","volume":"13","author":"Blumer","year":"1948","journal-title":"Am. Sociol. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1111\/jcc4.12102","article-title":"Social media analysis and public opinion: The 2010 UK general election","volume":"37","author":"Anstead","year":"2015","journal-title":"J. Comput. Mediat. Commun."},{"key":"ref_21","unstructured":"Bryce, J. (1888). The American Commonwealth, Macmillan."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1080\/10584600152647146","article-title":"Public opinion infrastructures: Meanings, measures, media","volume":"18","author":"Herbst","year":"2001","journal-title":"Political Commun."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1007\/s11135-014-0078-8","article-title":"Unspeaking on Facebook? Testing network exposure effects on self-censorship of political expressions in social network sites","volume":"49","author":"Kwon","year":"2015","journal-title":"Qual. Quant."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1080\/01292986.2018.1453849","article-title":"Predicting elections from social media: A three-country, three-method comparative study","volume":"29","author":"Jaidka","year":"2019","journal-title":"Asian J. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1111\/j.1468-2885.2010.01375.x","article-title":"The duality of media: A structurational theory of public attention","volume":"21","author":"Webster","year":"2011","journal-title":"Commun. Theory"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1287\/orsc.11.3.270.12502","article-title":"When market information constitutes fields: Sensemaking of markets in the commercial music industry","volume":"11","author":"Anand","year":"2000","journal-title":"Organ. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1086\/265034","article-title":"Toward a science of Public opinion","volume":"1","author":"Allport","year":"1937","journal-title":"Public Opin. Q."},{"key":"ref_28","unstructured":"Fox, S. (2020, February 05). Four in Ten Seniors Go Online. Available online: http:\/\/www.pewinternet.org\/2010\/01\/13\/four-in-ten-seniors-go-online."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1080\/15205431003642707","article-title":"Does the digital divide matter more? Comparing the effects of new media and old media use on the education-based knowledge gap","volume":"14","author":"Wei","year":"2011","journal-title":"Mass Commun. Soc."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tumasjan, A., Sprenger, T.O., Sandner, P.G., and Welpe, I.M. (2010, January 23\u201326). Predicting elections with Twitter: What 140 characters reveal about political sentiment. Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, Washington, DC, USA.","DOI":"10.1609\/icwsm.v4i1.14009"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zaller, J. (1992). The Nature and Origins of Mass Opinion. Cambridge University Press.","DOI":"10.1017\/CBO9780511818691"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1111\/j.1468-2958.2011.01423.x","article-title":"Emotions, public opinion, and US presidential approval rates: A 5-year analysis of online political discussions","volume":"38","author":"Banchs","year":"2012","journal-title":"Hum. Commun. Res."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ibrahim, M., Abdillah, O., Wicaksono, A.F., and Adriani, M. (2015, January 14\u201317). Buzzer Detection and Sentiment Analysis for Predicting Presidential Election Results in a Twitter Nation. Proceedings of the 2015 IEEE International Conference on Data Mining Workshop (ICDMW), Atlantic City, NJ, USA.","DOI":"10.1109\/ICDMW.2015.113"},{"key":"ref_34","unstructured":"Li, H.L., Ng, V.T., and Shiu, S.C. (2013, January 27\u201329). Predicting short interval tracking polls with online social media. Proceedings of the 17th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Whistler, UK."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Contractor, D., and Faruquie, T.A. (2013, January 18\u201322). Understanding election candidate approval ratings using social media data. Proceedings of the 22nd International Conference on World Wide Web companion, Rio de Janeiro, Brazil.","DOI":"10.1145\/2487788.2487883"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"O\u2019Connor, B., Balasubramanyan, R., Routledge, B.R., and Smith, N.A. (2010, January 23\u201326). From tweets to polls: Linking text sentiment to public opinion time series. Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, Washington, DC, USA.","DOI":"10.1609\/icwsm.v4i1.14031"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wilson, T., Wiebe, J., and Hoffmann, P. (2005, January 6\u20138). Recognizing contextual polarity in phrase-level sentiment analysis. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, BC, Canada.","DOI":"10.3115\/1220575.1220619"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chung, J.E., and Mustafaraj, E. (2011, January 25\u201330). Can collective sentiment expressed on twitter predict political elections?. Proceedings of the 25th AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v25i1.8065"},{"key":"ref_39","unstructured":"Esuli, A., and Sebastiani, F. (2020, February 05). SentiWordNet: A High-Coverage Lexical Resource for Opinion Mining. Available online: http:\/\/nmis.isti.cnr.it\/sebastiani\/Publications\/2007TR02.pdf."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/2001269.2001297","article-title":"Don\u2019t turn social media into another \u2018Literary Digest\u2019 poll","volume":"54","year":"2011","journal-title":"Commun. ACM"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1111\/ajps.12274","article-title":"Predicting and interpolating state-level polls using Twitter textual data","volume":"61","author":"Beauchamp","year":"2017","journal-title":"Am. J. Political Sci."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Dwi Prasetyo, N., and Hauff, C. (2015, January 2\u20134). Twitter-based election prediction in the developing world. Proceedings of the 26th ACM Conference on Hypertext & Social Media, Guzelyurt, TRNC, Cyprus.","DOI":"10.1145\/2700171.2791033"},{"key":"ref_43","first-page":"280","article-title":"On predicting election results using Twitter and Linked Open data: The case of the UK 2010 election","volume":"23","author":"Kalampokis","year":"2015","journal-title":"J. Univers. Comput. Sci."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Monti, C., Zignani, M., Rozza, A., Arvidsson, A., Zappella, G., and Colleoni, E. (2013, January 11). Modelling political disaffection from twitter data. Proceedings of the 2nd International Workshop on Issues of Sentiment Discovery and Opinion Mining, Chicago, IL, USA.","DOI":"10.1145\/2502069.2502072"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Sharma, P., and Moh, T.S. (2016, January 5\u20138). Prediction of Indian election using sentiment analysis on Hindi Twitter. Proceedings of the 2016 IEEE International Conference on Big Data, Washington, DC, USA.","DOI":"10.1109\/BigData.2016.7840818"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Huberty, M.E. (2013, January 28). Multi-cycle forecasting of congressional elections with social media. Proceedings of the 2nd workshop on Politics, Elections and Data, San Francisco, CA, USA.","DOI":"10.1145\/2508436.2508439"},{"key":"ref_47","unstructured":"Xie, Z., Liu, G., Wu, J., Wang, L., and Liu, C. (2016, January 24\u201326). Wisdom of fusion: Prediction of 2016 Taiwan election with heterogeneous big data. Proceedings of the 13th International Conference on Service Systems and Service Management (ICSSSM), Kunming, China."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Mejova, Y., Srinivasan, P., and Boynton, B. (2013, January 4\u20138). GOP primary season on twitter: Popular political sentiment in social media. Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, Rome, Italy.","DOI":"10.1145\/2433396.2433463"},{"key":"ref_49","unstructured":"Livne, A., Simmons, M.P., Adar, E., and Adamic, L.A. (2011, January 17\u201321). The party is over here: Structure and content in the 2010 election. Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, Barcelona, Spain."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.giq.2017.05.004","article-title":"Facebook likes and public opinion: Predicting the 2015 Finnish parliamentary elections","volume":"34","author":"Li","year":"2017","journal-title":"Gov. Inf. Q."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Metaxas, P.T., Mustafaraj, E., and Gayo-Avello, D. (2011, January 9\u201311). How (not) to predict elections. Proceedings of the 2011 IEEE Third International Conference on Social Computing (SocialCom), Boston, MA, USA.","DOI":"10.1109\/PASSAT\/SocialCom.2011.98"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1017\/S1049096515000797","article-title":"Forecasting congressional elections using facebook data","volume":"48","author":"MacWilliams","year":"2015","journal-title":"PS Political Sci. Politics"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Pimenta, F., Obradovic, D., and Dengel, A. (2013, January 27\u201329). A comparative study of social media prediction potential in the 2012 US republican presidential preelections. Proceedings of the 3rd International Conference on Cloud and Green Computing, Dublin, Ireland.","DOI":"10.1109\/CGC.2013.43"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1108\/IntR-06-2012-0114","article-title":"Understanding the predictive power of social media","volume":"23","author":"Metaxas","year":"2013","journal-title":"Internet Res."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1080\/02185377.2015.1020319","article-title":"India 2014: Facebook \u2018like\u2019as a predictor of election outcomes","volume":"23","author":"Barclay","year":"2015","journal-title":"Asian J. Political Sci."},{"key":"ref_56","unstructured":"Williams, C., and Gulati, G. (2008, January 6\u201327). What is a social network worth? Facebook and vote share in the 2008 presidential primaries. Proceedings of the 2008 Annual Meeting of the American Political Science Association, Boston, MA, USA."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","article-title":"Centrality in social networks conceptual clarification","volume":"1","author":"Freeman","year":"1979","journal-title":"Soc. Netw."},{"key":"ref_58","unstructured":"Page, L., Brin, S., Motwani, R., and Winograd, T. (2020, February 05). The PageRank Citation Ranking: Bringing Order to the Web. Available online: http:\/\/homepages.dcc.ufmg.br\/~nivio\/cursos\/ri11\/sources\/pagerank.pdf."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1080\/15377857.2014.959690","article-title":"Can social media predict election results? Evidence from new zealand","volume":"15","author":"Cameron","year":"2016","journal-title":"J. Political Mark."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Skoric, M.M., Poor, N.D., Achananuparp, P., Lim, E.P., and Jiang, J. (2012, January 4\u20137). Tweets and votes: A study of the 2011 Singapore General Election. Proceedings of the 45th Hawaii International Conference on System Sciences, Maui, HI, USA.","DOI":"10.1109\/HICSS.2012.607"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"DiGrazia, J., McKelvey, K., Bollen, J., and Rojas, F. (2013). More tweets, more votes: Social media as a quantitative indicator of political behavior. PLoS ONE, 8.","DOI":"10.2139\/ssrn.2235423"},{"key":"ref_62","first-page":"301","article-title":"Issues in presidential election forecasting: Election margins, incumbency, and model credibility","volume":"47","author":"Campbell","year":"2014","journal-title":"PS: Political Sci. Politics"},{"key":"ref_63","unstructured":"Krasno, J.S. (1994). Challengers, Competition, and Reelection: Comparing House and Senate Elections, Yale University Press."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1126\/science.1230456","article-title":"Social media and the elections","volume":"338","author":"Metaxas","year":"2012","journal-title":"Science"},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1080\/19331681.2012.705080","article-title":"Wisdom of the Crowds: 2010 UK election prediction with social media","volume":"10","author":"Franch","year":"2013","journal-title":"J. Inf. Technol. Politics"},{"key":"ref_66","unstructured":"Gayo-Avello, D., Metaxas, P.T., and Mustafaraj, E. (2011, January 17\u201321). Limits of electoral predictions using twitter. Proceedings of the ICWSM, Barcelona, Spain."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Gaurav, M., Srivastava, A., Kumar, A., and Miller, S. (2013, January 21\u201323). Leveraging candidate popularity on Twitter to predict election outcome. Proceedings of the 7th Workshop on Social Network Mining and Analysis, Chicago, IL, USA.","DOI":"10.1145\/2501025.2501038"},{"key":"ref_68","unstructured":"Kuhn, T.S. (1962). The Structure of Scientific Revolutions, University of Chicago Press."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/4\/187\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:13:48Z","timestamp":1760174028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/11\/4\/187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,31]]},"references-count":68,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,4]]}},"alternative-id":["info11040187"],"URL":"https:\/\/doi.org\/10.3390\/info11040187","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,31]]}}}