{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T02:36:53Z","timestamp":1769308613612,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Albert-Ludwigs-Universit\u00e4t Freiburg im Breisgau"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Google trends (GT), a service aggregating search queries on Google, has been used to predict various outcomes such as as the spread of influenza, automobile sales, unemployment claims, and travel destination planning [1, 2]. Social scientists also used GT to predict elections and referendums across different countries and time periods, sometimes with more, sometimes with less success. We provide unique evidence on the predictive power of GT in the German multi-party systems, forecasting four elections (2009, 2013, 2017, 2021). Thereby, we make several contributions: First, we present one of the first attempts to predict a multi-party election using GT and highlight the specific challenges that originate from this setting. In doing so, we also provide a comprehensive and systematic overview of prior research. Second, we develop a framework that allows for fine-grained variation of the GT data window both in terms of its width and distance to the election. Subsequently, we test the predictive accuracy of several thousand models resulting from those fine-grained specifications. Third, we compare the predictive power of different model classes that are purely GT data based but also incorporate polling data as well as previous elections. Finally, we provide a systematic overview of the challenges one faces in using GT data for predictions part of which have been neglected in prior research.<\/jats:p>","DOI":"10.1186\/s40537-023-00868-4","type":"journal-article","created":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T15:02:42Z","timestamp":1708182162000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Can we predict multi-party elections with Google Trends data? Evidence across elections, data windows, and model classes"],"prefix":"10.1186","volume":"11","author":[{"given":"Jan","family":"Behnert","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dean","family":"Lajic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul C.","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,17]]},"reference":[{"key":"868_CR1","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/j.1475-4932.2012.00809.x","volume":"88","author":"H Choi","year":"2012","unstructured":"Choi H, Varian H. Predicting the present with Google trends. Economic Record. 2012;88:2\u20139.","journal-title":"Economic Record"},{"issue":"7232","key":"868_CR2","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1038\/nature07634","volume":"457","author":"J Ginsberg","year":"2009","unstructured":"Ginsberg J, Mohebbi MH, Patel RS, Brammer L, Smolinski MS, Brilliant L. Detecting influenza epidemics using search engine query data. Nature. 2009;457(7232):1012\u20134.","journal-title":"Nature"},{"issue":"4","key":"868_CR3","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1177\/0002764220975067","volume":"65","author":"C Prado-Rom\u00e1n","year":"2021","unstructured":"Prado-Rom\u00e1n C, G\u00f3mez-Mart\u00ednez R, Orden-Cruz C. Google trends as a predictor of presidential elections: The United States versus Canada. Am Behav Sci. 2021;65(4):666\u201380.","journal-title":"Am Behav Sci"},{"issue":"2","key":"868_CR4","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1017\/pan.2018.49","volume":"27","author":"LF Stoetzer","year":"2019","unstructured":"Stoetzer LF, Neunhoeffer M, Gschwend T, Munzert S, Sternberg S. Forecasting elections in multiparty systems: a Bayesian approach combining polls and fundamentals. Polit Anal. 2019;27(2):255\u201362.","journal-title":"Polit Anal"},{"issue":"3","key":"868_CR5","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1016\/j.ijforecast.2014.06.001","volume":"31","author":"W Wang","year":"2015","unstructured":"Wang W, Rothschild D, Goel S, Gelman A. Forecasting elections with non-representative polls. Int J Forecast. 2015;31(3):980\u201391.","journal-title":"Int J Forecast"},{"issue":"2","key":"868_CR6","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1017\/S1049096513000292","volume":"46","author":"L Granka","year":"2013","unstructured":"Granka L. Using online search traffic to predict US presidential elections. PS Polit Sci Polit. 2013;46(2):271\u20139.","journal-title":"PS Polit Sci Polit"},{"key":"868_CR7","unstructured":"D21 I. Share of internet users in Germany from 2001 to 2021 Graph]. Statista. 2022. https:\/\/www.statista.com\/statistics\/380514\/internet-usage-rate-germany\/"},{"key":"868_CR8","unstructured":"StatCounter. Desktop and mobile search market share of search engines in Germany in December 2023 [Graph]. Statista. 2023. https:\/\/www.statista.com\/statistics\/445974\/search-engines-market-share-of-desktop-and-mobile-search-germany\/"},{"key":"868_CR9","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.techfore.2017.11.009","volume":"130","author":"SP Jun","year":"2018","unstructured":"Jun SP, Yoo HS, Choi S. Ten years of research change using Google trends: from the perspective of big data utilizations and applications. Technol Forecast Soc Change. 2018;130:69\u201387.","journal-title":"Technol Forecast Soc Change"},{"issue":"8","key":"868_CR10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007258","volume":"15","author":"S Kandula","year":"2019","unstructured":"Kandula S, Shaman J. Reappraising the utility of Google Flu trends. PLoS Computat Biol. 2019;15(8): e1007258. https:\/\/doi.org\/10.1371\/journal.pcbi.1007258.","journal-title":"PLoS Computat Biol"},{"key":"868_CR11","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1126\/science.1248506","volume":"343","author":"D Lazer","year":"2014","unstructured":"Lazer D, Kennedy R, King G, Vespignani A. The parable of Google Flu: traps in big data analysis. Science. 2014;343:1203\u20135. https:\/\/doi.org\/10.1126\/science.1248506.","journal-title":"Science"},{"issue":"47","key":"868_CR12","doi-asserted-by":"publisher","first-page":"14473","DOI":"10.1073\/pnas.1515373112","volume":"112","author":"S Yang","year":"2015","unstructured":"Yang S, Santillana M, Kou SC. Accurate estimation of influenza epidemics using Google search data via ARGO. Proc Natl Acad Sci. 2015;112(47):14473\u20138.","journal-title":"Proc Natl Acad Sci"},{"key":"868_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpubeco.2020.104346","volume":"193","author":"A Brodeur","year":"2021","unstructured":"Brodeur A, Clark AE, Fleche S, Powdthavee N. COVID-19, lockdowns and well-being: evidence from Google trends. J Publ Econom. 2021;193: 104346.","journal-title":"J Publ Econom"},{"key":"868_CR14","doi-asserted-by":"publisher","unstructured":"Polykalas SE, Prezerakos GN, Konidaris A. A General Purpose Model for Future Prediction Based on Web Search Data: Predicting Greek and Spanish Election. In: 2013 27th International Conference on Advanced Information Networking and Applications Workshops. 2013. p. 213\u20138. https:\/\/doi.org\/10.1109\/WAINA.2013.155","DOI":"10.1109\/WAINA.2013.155"},{"key":"868_CR15","volume-title":"Trending in the right direction: using Google trends data as a measure of public opinion during a presidential election","author":"JT Wolf","year":"2018","unstructured":"Wolf JT. Trending in the right direction: using Google trends data as a measure of public opinion during a presidential election. Blacksburg: Virginia Tech; 2018."},{"key":"868_CR16","doi-asserted-by":"crossref","unstructured":"Askitas N. Calling the Greek Referendum on the Nose with Google Trends. SSRN Electron J. 2015. https:\/\/doi.org\/10.2139%2Fssrn.2708382","DOI":"10.2139\/ssrn.2633443"},{"key":"868_CR17","doi-asserted-by":"crossref","unstructured":"Askitas N. Predicting the Irish\u2019Gay Marriage\u2019Referendum. SSRN 2674243. 2015.","DOI":"10.2139\/ssrn.2708383"},{"issue":"1","key":"868_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-018-0166-z","volume":"6","author":"A Mavragani","year":"2019","unstructured":"Mavragani A, Tsagarakis KP. Predicting referendum results in the big data Era. J Big Data. 2019;6(1):1\u201320.","journal-title":"J Big Data"},{"key":"868_CR19","doi-asserted-by":"crossref","unstructured":"Polykalas SE, Prezerakos GN, Konidaris A. An algorithm based on Google Trends\u2019 data for future prediction. Case study: German elections. IEEE International Symposium on Signal Processing and Information Technology; 2013. p. 000069\u201373.","DOI":"10.1109\/ISSPIT.2013.6781856"},{"key":"868_CR20","unstructured":"Sj\u00f6vill R. Using Search Query Data to Predict the General Election: Can Google trends help predict the Swedish General Election? 2020."},{"key":"868_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.drugpo.2020.103083","volume":"90","author":"JE Raubenheimer","year":"2021","unstructured":"Raubenheimer JE, Riordan BC, Merrill JE, Winter T, Ward RM, Scarf D, et al. Hey Google! Will New Zealand vote to legalise cannabis? Using Google trends data to predict the outcome of the 2020 New Zealand cannabis referendum. Int J Drug Policy. 2021;90: 103083.","journal-title":"Int J Drug Policy"},{"issue":"9","key":"868_CR22","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1093\/aje\/kwac088","volume":"191","author":"JE Raubenheimer","year":"2022","unstructured":"Raubenheimer JE. A practical algorithm for extracting multiple data samples from google trends extended for health. Am J Epidemiol. 2022;191(9):1666\u20139.","journal-title":"Am J Epidemiol"},{"key":"868_CR23","doi-asserted-by":"crossref","unstructured":"Mavragani A, Tsagarakis KP. YES or NO: Predicting the 2015 GReferendum results using Google Trends. Technological Forecasting and Social Change. 2016;109:1\u20135. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0040162516300580","DOI":"10.1016\/j.techfore.2016.04.028"},{"key":"868_CR24","volume-title":"Predicting the results of the 2019 Indonesian presidential election with Google trends Asia-Pacific research in social sciences and humanities Universitas Indonesia (APRISH 2019)","author":"AA Harkan","year":"2021","unstructured":"Harkan AA. Predicting the results of the 2019 Indonesian presidential election with Google trends Asia-Pacific research in social sciences and humanities Universitas Indonesia (APRISH 2019). Amsterdam: Atlantis Press; 2021."},{"key":"868_CR25","doi-asserted-by":"publisher","unstructured":"Yasseri T, Bright J. Can electoral popularity be predicted using socially generated big data? Abstract it - Information Technology. 2014;56(5):246\u2013253. https:\/\/doi.org\/10.1515\/itit-2014-1046","DOI":"10.1515\/itit-2014-1046"},{"issue":"11","key":"868_CR26","doi-asserted-by":"publisher","first-page":"143","DOI":"10.3390\/data7110143","volume":"7","author":"F Vergara-Perucich","year":"2022","unstructured":"Vergara-Perucich, F. Assessing the accuracy of Google trends for predicting presidential elections: The case of Chile 2006\u20132021. Data. 2022;7(11):143. https:\/\/doi.org\/10.3390\/data7110143","journal-title":"Data"},{"key":"868_CR27","unstructured":"Help GT. FAQ about Google Trends data - Trends Help. 2023. https:\/\/support.google.com\/trends\/answer\/4365533?hl=en &amp%3Bref_topic=6248052"},{"key":"868_CR28","unstructured":"Help GT. Refine Trends results by category - Trends Help. 2023. https:\/\/support.google.com\/trends\/answer\/4359597?hl=en &ref_topic=4365530"},{"issue":"2","key":"868_CR29","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1111\/ecin.13049","volume":"60","author":"VZ Eichenauer","year":"2022","unstructured":"Eichenauer VZ, Indergand R, Mart\u00ednez IZ, Sax C. Obtaining consistent time series from Google Trends. Econom Inquiry. 2022;60(2):694\u2013705.","journal-title":"Econom Inquiry"},{"key":"868_CR30","unstructured":"Stephens-Davidowitz S, Varian H. A hands-on guide to google data. further details on the construction can be found on the Google Trends page. 2014;"},{"issue":"7","key":"868_CR31","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1080\/01402382.2022.2045783","volume":"45","author":"T Faas","year":"2022","unstructured":"Faas T, Klingelh\u00f6fer T. German politics at the traffic light: new beginnings in the election of 2021. West Eur Polit. 2022;45(7):1506\u201321. https:\/\/doi.org\/10.1080\/01402382.2022.2045783.","journal-title":"West Eur Polit"},{"key":"868_CR32","doi-asserted-by":"publisher","unstructured":"Mehltretter J, Keusch F, and Sajons C. The (mis)use of Google Trends data in the social sciences - A systematic review, critique, and guidelines. Working paper. 2023;1\u201355. https:\/\/doi.org\/10.17605\/OSF.IO\/CTN63","DOI":"10.17605\/OSF.IO\/CTN63"},{"issue":"1","key":"868_CR33","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1017\/S1049096521000913","volume":"55","author":"T Gschwend","year":"2022","unstructured":"Gschwend T, M\u00fcller K, Munzert S, Neunhoeffer M, Stoetzer LF. The Zweitstimme model: a dynamic forecast of the 2021 German federal election. PS Polit Sci Polit. 2022;55(1):85\u201390.","journal-title":"PS Polit Sci Polit"},{"key":"868_CR34","doi-asserted-by":"crossref","unstructured":"Munzert S, St\u00f6tzer L, Gschwend T, Neunhoeffer M, Sternberg S. Zweitstimme. Org. Ein strukturell-dynamisches Vorhersagemodell f\u00fcr Bundestagswahlen. Politische Vierteljahresschrift. 2017;418\u201341.","DOI":"10.5771\/0032-3470-2017-3-418"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00868-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-023-00868-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00868-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T15:05:15Z","timestamp":1708182315000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-023-00868-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,17]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["868"],"URL":"https:\/\/doi.org\/10.1186\/s40537-023-00868-4","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,17]]},"assertion":[{"value":"14 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare consent to publish.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests in relation to this research, whether fnancial, personal, authorship or otherwise, that could afect the research and its results presented in this paper","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"30"}}