{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:17:32Z","timestamp":1790011052253,"version":"4.0.1"},"reference-count":92,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Social Science Computer Review"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:p>\u201cSynthetic samples\u201d generated by large language models (LLMs) have been argued to complement or replace traditional surveys, assuming their training data is grounded in human-generated data that potentially reflects attitudes and behaviors prevalent in the population. Initial US-based studies that have prompted LLMs to mimic survey respondents found that the responses match survey data. However, the relationship between the respective target population and LLM training data might affect the generalizability of such findings. In this paper, we critically evaluate the use of LLMs for public opinion research in a different context, by investigating whether LLMs can estimate vote choice in Germany. We generate a synthetic sample matching the 2017 German Longitudinal Election Study respondents and ask the LLM GPT-3.5 to predict each respondent\u2019s vote choice. Comparing these predictions to the survey-based estimates on the aggregate and subgroup levels, we find that GPT-3.5 exhibits a bias towards the Green and Left parties. While the LLM predictions capture the tendencies of \u201ctypical\u201d voters, they miss more complex factors of vote choice. By examining the LLM-based prediction of voting behavior in a non-English speaking context, our study contributes to research on the extent to which LLMs can be leveraged for studying public opinion. The findings point to disparities in opinion representation in LLMs and underscore the limitations in applying them for public opinion estimation.<\/jats:p>","DOI":"10.1177\/08944393251337014","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T12:10:08Z","timestamp":1745669408000},"page":"549-571","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":8,"title":["Vox Populi, Vox AI? Using Large Language Models to Estimate German Vote Choice"],"prefix":"10.1177","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8992-0251","authenticated-orcid":false,"given":"Leah","family":"von der Heyde","sequence":"first","affiliation":[{"name":"LMU Munich"},{"name":"Munich Center for Machine Learning"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6772-0393","authenticated-orcid":false,"given":"Anna-Carolina","family":"Haensch","sequence":"additional","affiliation":[{"name":"LMU Munich"},{"name":"University of Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4621-2418","authenticated-orcid":false,"given":"Alexander","family":"Wenz","sequence":"additional","affiliation":[{"name":"University of Mannheim"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"e_1_3_8_2_1","volume-title":"Aaru: Rethinking the science of prediction","author":"Aaru","unstructured":"Aaru. (n.d.). Aaru: Rethinking the science of prediction. https:\/\/aaruaaru.com"},{"key":"e_1_3_8_3_1","volume-title":"Extracting affect aggregates from longitudinal social media data with temporal adapters for large language models","author":"Ahnert G.","year":"2024","unstructured":"Ahnert G., Pellert M., Garcia D., Strohmaier M. (2024). Extracting affect aggregates from longitudinal social media data with temporal adapters for large language models (No. arXiv:2409.17990). arXiv. https:\/\/arxiv.org\/abs\/2409.17990"},{"key":"e_1_3_8_4_1","volume-title":"Marginaleffects: Predictions, comparisons, slopes, marginal means, and hypothesis tests","author":"Arel-Bundock V.","year":"2021","unstructured":"Arel-Bundock V. (2021). Marginaleffects: Predictions, comparisons, slopes, marginal means, and hypothesis tests (p. 0.21.0) [Dataset]. https:\/\/doi.org\/10.32614\/CRAN.package.marginaleffects"},{"key":"e_1_3_8_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2023.2"},{"key":"e_1_3_8_6_1","volume-title":"Understanding jailbreak success: A study of latent space dynamics in large language models","author":"Ball S.","year":"2024","unstructured":"Ball S., Kreuter F., Panickssery N. (2024). Understanding jailbreak success: A study of latent space dynamics in large language models (arXiv: 2406.09289). arXiv. https:\/\/arxiv.org\/abs\/2406.09289"},{"key":"e_1_3_8_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/0199273219.003.0005"},{"key":"e_1_3_8_8_1","doi-asserted-by":"crossref","unstructured":"Bianchi F. Kalluri P. Durmus E. Ladhak F. Cheng M. Nozza D. Hashimoto T. Jurafsky D. Zou J. Caliskan A. (2023). Easily accessible text-to-image generation amplifies demographic stereotypes at large scale. In 2023 ACM conference on fairness accountability and transparency Chicago IL USA 12\u201315 June 2023 pp. 1493\u20131504. https:\/\/doi.org\/10.1145\/3593013.3594095","DOI":"10.1145\/3593013.3594095"},{"key":"e_1_3_8_9_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2024.5"},{"key":"e_1_3_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2004.06.005"},{"key":"e_1_3_8_11_1","volume-title":"Language models are few-shot learners","author":"Brown T. B.","year":"2020","unstructured":"Brown T. B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D. M., Wu J., Winter C., Amodei D. (2020). Language models are few-shot learners (arXiv:2005.14165). arXiv. https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_8_12_1","volume-title":"The American voter","author":"Campbell A.","year":"1960","unstructured":"Campbell A., Converse P. E., Miller W. E., Stokes D. E. (1960). The American voter (University of Michigan, Ed.; Unabridged ed). University of Chicago Press."},{"key":"e_1_3_8_13_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4572954"},{"key":"e_1_3_8_14_1","volume-title":"Language models trained on media diets can predict public opinion","author":"Chu E.","year":"2023","unstructured":"Chu E., Andreas J., Ansolabehere S., Roy D. (2023). Language models trained on media diets can predict public opinion (arXiv:2303.16779). arXiv. https:\/\/arxiv.org\/abs\/2303.16779"},{"key":"e_1_3_8_15_1","volume-title":"An AI polling startup makes its predictions for the 2024 US election","author":"Chua G.","year":"2024","unstructured":"Chua G. (2024, November 5). An AI polling startup makes its predictions for the 2024 US election. Semafor. https:\/\/www.semafor.com\/article\/11\/04\/2024\/an-ai-polling-startup-polls-bots-predicts-harris-will-win"},{"key":"e_1_3_8_16_1","volume-title":"Data representativity for machine learning and AI systems","author":"Clemmensen L. H.","year":"2023","unstructured":"Clemmensen L. H., Kj\u00e6rsgaard R. D. (2023). Data representativity for machine learning and AI systems (arXiv:2203.04706). arXiv. https:\/\/arxiv.org\/abs\/2203.04706"},{"key":"e_1_3_8_17_1","first-page":"1","article-title":"Assessing data quality in the age of digital social research: A systematic review","author":"Daikeler J.","year":"2024","unstructured":"Daikeler J., Fr\u00f6hling L., Sen I., Birkenmaier L., Gummer T., Schwalbach J., Silber H., Wei\u00df B., Weller K., Lechner C. (2024). Assessing data quality in the age of digital social research: A systematic review. Social Science Computer Review, 1\u201337. https:\/\/doi.org\/10.1177\/08944393241245395","journal-title":"Social Science Computer Review"},{"key":"e_1_3_8_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-137-30164-2_4"},{"key":"e_1_3_8_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198830986.001.0001"},{"key":"e_1_3_8_20_1","unstructured":"Delve AI (nd). AI persona generator. https:\/\/www.delve.ai\/ai-persona-generator"},{"key":"e_1_3_8_21_1","volume-title":"Questioning the survey responses of large language models","author":"Dominguez-Olmedo R.","year":"2023","unstructured":"Dominguez-Olmedo R., Hardt M., Mendler-D\u00fcnner C. (2023). Questioning the survey responses of large language models (arXiv:2306.07951). arXiv. https:\/\/arxiv.org\/abs\/2306.07951"},{"key":"e_1_3_8_22_1","volume-title":"Towards measuring the representation of subjective global opinions in language models","author":"Durmus E.","year":"2023","unstructured":"Durmus E., Nyugen K., Liao T. I., Schiefer N., Askell A., Bakhtin A., Chen C., Hatfield-Dodds Z., Hernandez D., Joseph N., Lovitt L., McCandlish S., Sikder O., Tamkin A., Thamkul J., Kaplan J., Clark J., Ganguli D. (2023). Towards measuring the representation of subjective global opinions in language models (arXiv:2306.16388). arXiv. https:\/\/arxiv.org\/abs\/2306.16388"},{"key":"e_1_3_8_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/09644008.2011.554109"},{"key":"e_1_3_8_24_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-polisci-052217-104957"},{"key":"e_1_3_8_25_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511616884"},{"key":"e_1_3_8_26_1","unstructured":"GLES. (2019). Post-election cross section (GLES 2017) Nachwahl-Querschnitt (GLES 2017) (4.0.1) [Dataset]. GESIS Data Archive. https:\/\/doi.org\/10.4232\/1.13235"},{"key":"e_1_3_8_27_1","doi-asserted-by":"publisher","DOI":"10.1037\/met0000540"},{"key":"e_1_3_8_28_1","volume-title":"The political ideology of conversational AI: Converging evidence on ChatGPT\u2019s pro-environmental, left-libertarian orientation","author":"Hartmann J.","year":"2023","unstructured":"Hartmann J., Schwenzow J., Witte M. (2023). The political ideology of conversational AI: Converging evidence on ChatGPT\u2019s pro-environmental, left-libertarian orientation (arXiv:2301.01768). arXiv. https:\/\/arxiv.org\/abs\/2301.01768"},{"key":"e_1_3_8_29_1","volume-title":"Multilingual Language models are not multicultural: A case study in emotion","author":"Havaldar S.","year":"2023","unstructured":"Havaldar S., Rai S., Singhal B., Liu L., Guntuku S. C., Ungar L. (2023). Multilingual Language models are not multicultural: A case study in emotion (No. arXiv:2307.01370). arXiv. https:\/\/arxiv.org\/abs\/2307.01370"},{"key":"e_1_3_8_30_1","volume-title":"Marginalia: A guide to figuring out what the heck marginal effects, marginal slopes, average marginal effects, marginal effects at the mean, and all these other marginal things are","author":"Heiss A.","year":"2022","unstructured":"Heiss A. (2022, May 22). Marginalia: A guide to figuring out what the heck marginal effects, marginal slopes, average marginal effects, marginal effects at the mean, and all these other marginal things are. Andrew Heiss. https:\/\/www.andrewheiss.com\/blog\/2022\/05\/20\/marginalia\/#what-are-marginal-effects"},{"key":"e_1_3_8_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/peps.12543"},{"key":"e_1_3_8_32_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0065782"},{"key":"e_1_3_8_33_1","doi-asserted-by":"publisher","DOI":"10.31219\/osf.io\/udz28"},{"key":"e_1_3_8_34_1","volume-title":"The silent revolution: Changing values and political styles among Western publics","author":"Inglehart R.","year":"1977","unstructured":"Inglehart R. (1977). The silent revolution: Changing values and political styles among Western publics. Princeton University Press."},{"key":"e_1_3_8_35_1","volume-title":"Measuring digital development: Facts and figures 2022","author":"International Telecommunication Union.","year":"2022","unstructured":"International Telecommunication Union. (2022, July 2). Measuring digital development: Facts and figures 2022. https:\/\/www.itu.int\/hub\/publication\/d-ind-ict_mdd-2022\/."},{"key":"e_1_3_8_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06259-9"},{"key":"e_1_3_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2012.09.007"},{"key":"e_1_3_8_38_1","volume-title":"The Ghost in the Machine has an American accent: Value conflict in GPT-3","author":"Johnson R. L.","year":"2022","unstructured":"Johnson R. L., Pistilli G., Men\u00e9dez-Gonz\u00e1lez N., Duran L. D. D., Panai E., Kalpokiene J., Bertulfo D. J. (2022). The Ghost in the Machine has an American accent: Value conflict in GPT-3 (arXiv:2203.07785). arXiv. https:\/\/arxiv.org\/abs\/2203.07785"},{"key":"e_1_3_8_39_1","volume-title":"AI-augmented surveys: Leveraging large language models and surveys for opinion prediction","author":"Kim J.","year":"2023","unstructured":"Kim J., Lee B. (2023). AI-augmented surveys: Leveraging large language models and surveys for opinion prediction (arXiv:2305.09620). arXiv. https:\/\/arxiv.org\/abs\/2305.09620"},{"key":"e_1_3_8_40_1","doi-asserted-by":"publisher","DOI":"10.1093\/joc\/jqab034"},{"key":"e_1_3_8_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-05164-8_13"},{"key":"e_1_3_8_42_1","volume-title":"rgpt3: Making requests from R to the GPT-3 API and ChatGPT","author":"Kleinberg B.","year":"2023","unstructured":"Kleinberg B. (2023). rgpt3: Making requests from R to the GPT-3 API and ChatGPT. R package version 0.4. https:\/\/github.com\/ben-aaron188\/rgpt3"},{"key":"e_1_3_8_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00312-6"},{"key":"e_1_3_8_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-6765.2006.00644.x"},{"key":"e_1_3_8_45_1","doi-asserted-by":"crossref","unstructured":"Lai V. Ngo N. Pouran Ben Veyseh A. Man H. Dernoncourt F. Bui T. Nguyen T. (2023). ChatGPT beyond English: Towards a Comprehensive evaluation of large language models in multilingual learning. Findings of the Association for Computational Linguistics: EMNLP 2023 13171\u201313189. https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.878","DOI":"10.18653\/v1\/2023.findings-emnlp.878"},{"key":"e_1_3_8_46_1","doi-asserted-by":"publisher","DOI":"10.31234\/osf.io\/rqa9m"},{"key":"e_1_3_8_47_1","volume-title":"The people\u2019s choice: How the voter makes up his mind in a presidential campaign","author":"Lazarsfeld P. F.","year":"1944","unstructured":"Lazarsfeld P. F., Berelson B., Gaudet-Erskine H. (1944). The people\u2019s choice: How the voter makes up his mind in a presidential campaign (Legacy edition). Columbia University Press."},{"key":"e_1_3_8_48_1","volume-title":"Detecting the corruption of online questionnaires by artificial intelligence","author":"Lebrun B.","year":"2023","unstructured":"Lebrun B., Temtsin S., Vonasch A., Bartneck C. (2023). Detecting the corruption of online questionnaires by artificial intelligence (arXiv:2308.07499). arXiv. https:\/\/arxiv.org\/abs\/2308.07499"},{"key":"e_1_3_8_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10869-022-09864-6"},{"key":"e_1_3_8_50_1","doi-asserted-by":"crossref","unstructured":"Li B. Haider S. Callison-Burch C. (2024). This land is your my land: Evaluating geopolitical bias in language models through territorial disputes. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Mexico City Mexico June 2024 3855\u20133871. https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.213","DOI":"10.18653\/v1\/2024.naacl-long.213"},{"key":"e_1_3_8_51_1","volume-title":"Using large language models to generate engaging captions for data visualizations","author":"Liew A.","year":"2022","unstructured":"Liew A., Mueller K. (2022). Using large language models to generate engaging captions for data visualizations (arXiv:2212.14047). arXiv. https:\/\/arxiv.org\/abs\/2212.14047"},{"key":"e_1_3_8_52_1","first-page":"1","volume-title":"Party systems and voter alignments: Cross\u2010national perspectives","author":"Lipset S. M.","year":"1967","unstructured":"Lipset S. M., Rokkan S. (1967). Cleavage structures, party systems, and voter alignments. An introduction. In Lipset S. M., Rokkan S. (Eds.), Party systems and voter alignments: Cross\u2010national perspectives (pp. 1\u201364). Collier-Macmillan."},{"key":"e_1_3_8_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbe2.140"},{"key":"e_1_3_8_54_1","volume-title":"Embers of autoregression: Understanding large language models through the problem they are trained to solve","author":"McCoy R. T.","year":"2023","unstructured":"McCoy R. T., Yao S., Friedman D., Hardy M., Griffiths T. L. (2023). Embers of autoregression: Understanding large language models through the problem they are trained to solve (arXiv:2309.13638). arXiv. https:\/\/arxiv.org\/abs\/2309.13638"},{"key":"e_1_3_8_55_1","doi-asserted-by":"publisher","DOI":"10.1177\/20531680241231468"},{"key":"e_1_3_8_56_1","article-title":"AI polling company defends wrong predictions on the US election","author":"Mendoza D.","year":"2024","unstructured":"Mendoza D. (2024, November 6). AI polling company defends wrong predictions on the US election. Semafor. https:\/\/www.semafor.com\/article\/11\/06\/2024\/ai-startup-aaru-defends-using-artificial-intelligence-for-polling","journal-title":"Semafor"},{"issue":"3","key":"e_1_3_8_57_1","first-page":"3","article-title":"More human than human: Measuring ChatGPT political bias","volume":"198","author":"Motoki F.","year":"2023","unstructured":"Motoki F., Neto V. P., Rodrigues V. (2023). More human than human: Measuring ChatGPT political bias. Public Choice, 198(3), 3\u201323. https:\/\/doi.org\/10.1007\/s11127-023-01097-2","journal-title":"Public Choice"},{"key":"e_1_3_8_58_1","doi-asserted-by":"publisher","DOI":"10.1515\/comm.2003.009"},{"key":"e_1_3_8_59_1","article-title":"Humans are biased. Generative AI is even worse","author":"Nicoletti L.","year":"2023","unstructured":"Nicoletti L., Bass D. (2023, October 3). Humans are biased. Generative AI is even worse. Bloomberg.Com. https:\/\/www.bloomberg.com\/graphics\/2023-generative-ai-bias\/","journal-title":"Bloomberg.Com"},{"key":"e_1_3_8_60_1","volume-title":"BMIKE-53: Investigating cross-lingual knowledge editing with in-context learning","author":"Nie E.","year":"2024","unstructured":"Nie E., Shao B., Ding Z., Wang M., Schmid H., Sch\u00fctze H. (2024). BMIKE-53: Investigating cross-lingual knowledge editing with in-context learning (arXiv:2406.17764). arXiv. https:\/\/arxiv.org\/abs\/2406.17764"},{"key":"e_1_3_8_61_1","volume-title":"Decomposed prompting: Unveiling multilingual linguistic structure knowledge in English-centric large language models","author":"Nie E.","year":"2024","unstructured":"Nie E., Yuan S., Ma B., Schmid H., F\u00e4rber M., Kreuter F., Sch\u00fctze H. (2024). Decomposed prompting: Unveiling multilingual linguistic structure knowledge in English-centric large language models (arXiv:2402.18397). arXiv. https:\/\/arxiv.org\/abs\/2402.18397"},{"key":"e_1_3_8_62_1","volume-title":"Do the OpenAI API models have knowledge of current events?","author":"OpenAI","unstructured":"OpenAI. (n.d.). Do the OpenAI API models have knowledge of current events? https:\/\/help.openai.com\/en\/articles\/6639781-do-the-openai-api-models-have-knowledge-of-current-events"},{"key":"e_1_3_8_63_1","volume-title":"GPT-4 technical report","author":"OpenAI","year":"2023","unstructured":"OpenAI, Achiam J., Adler S., Agarwal S., Ahmad L., Akkaya I., Aleman F. L., Almeida D., Altenschmidt J., Altman S., Anadkat S., Avila R., Babuschkin I., Balaji S., Balcom V., Baltescu P., Bao H., Bavarian M., Belgum J., Zoph B. (2023). GPT-4 technical report (Version 6). arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2303.08774"},{"key":"e_1_3_8_64_1","volume-title":"GPT-4 API general availability and deprecation of older models in the Completions API","author":"OpenAI","year":"2024","unstructured":"OpenAI. (2024a, July 2). GPT-4 API general availability and deprecation of older models in the Completions API. https:\/\/openai.com\/index\/gpt-4-api-general-availability\/"},{"key":"e_1_3_8_65_1","volume-title":"Models\u2014OpenAI API","author":"OpenAI","year":"2024","unstructured":"OpenAI. (2024b, July 2). Models\u2014OpenAI API. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5-turbo"},{"key":"e_1_3_8_66_1","unstructured":"R Core Team. (2024). R: The R project for statistical computing. https:\/\/www.r-project.org\/"},{"key":"e_1_3_8_67_1","volume-title":"Ask a Llama - Creating variance in synthetic survey data","author":"Roth M.","year":"2024","unstructured":"Roth M. (2024). Ask a Llama - Creating variance in synthetic survey data. General Online Research (GOR 24), Rheinische Fachhochschule K\u00f6ln. February 22, 2024. https:\/\/doi.org\/10.17605\/OSF.IO\/CHBTR"},{"key":"e_1_3_8_68_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316696"},{"key":"e_1_3_8_69_1","volume-title":"Towards coding social science datasets with language models","author":"Rytting C. M.","year":"2023","unstructured":"Rytting C. M., Sorensen T., Argyle L., Busby E., Fulda N., Gubler J., Wingate D. (2023). Towards coding social science datasets with language models (arXiv:2306.02177). arXiv. https:\/\/arxiv.org\/abs\/2306.02177"},{"key":"e_1_3_8_70_1","volume-title":"Whose opinions do language models reflect?","author":"Santurkar S.","year":"2023","unstructured":"Santurkar S., Durmus E., Ladhak F., Lee C., Liang P., Hashimoto T. (2023). Whose opinions do language models reflect? (arXiv:2303.17548). arXiv. https:\/\/arxiv.org\/abs\/2303.17548"},{"key":"e_1_3_8_71_1","doi-asserted-by":"publisher","DOI":"10.1093\/sp\/jxac003"},{"key":"e_1_3_8_72_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198847519.003.0015"},{"key":"e_1_3_8_73_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198847519.003.0001"},{"key":"e_1_3_8_74_1","volume-title":"Voters and voting in context: Multiple contexts and the heterogeneous German electorate","author":"Schoen H.","year":"2017","unstructured":"Schoen H., Ro\u00dfteutscher S., Schmitt-Beck R., We\u00dfels B., Wolf C. (Eds.), (2017). Voters and voting in context: Multiple contexts and the heterogeneous German electorate (1st ed.). Oxford University Press.","edition":"1"},{"key":"e_1_3_8_75_1","volume-title":"8 charts on internet use around the world as countries grapple with COVID-19","author":"Schumacher S.","year":"2020","unstructured":"Schumacher S., Kent N. (2020). 8 charts on internet use around the world as countries grapple with COVID-19. Pew Research Center. https:\/\/www.pewresearch.org\/short-reads\/2020\/04\/02\/8-charts-on-internet-use-around-the-world-as-countries-grapple-with-covid-19\/"},{"key":"e_1_3_8_76_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-01295-4"},{"key":"e_1_3_8_77_1","doi-asserted-by":"publisher","DOI":"10.1080\/13645579.2020.1844896"},{"key":"e_1_3_8_78_1","volume-title":"DataTales: Investigating the use of large language models for authoring data-driven articles","author":"Sultanum N.","year":"2023","unstructured":"Sultanum N., Srinivasan A. (2023). DataTales: Investigating the use of large language models for authoring data-driven articles (arXiv:2308.04076). arXiv. https:\/\/arxiv.org\/abs\/2308.04076"},{"key":"e_1_3_8_79_1","volume-title":"Synthetic users","author":"Synthetic Users","unstructured":"Synthetic Users. (n.d.). Synthetic users. https:\/\/www.syntheticusers.com"},{"key":"e_1_3_8_80_1","volume-title":"LLaMA: Open and efficient foundation language models (version 1)","author":"Touvron H.","year":"2023","unstructured":"Touvron H., Lavril T., Izacard G., Martinet X., Lachaux M.-A., Lacroix T., Rozi\u00e8re B., Goyal N., Hambro E., Azhar F., Rodriguez A., Joulin A., Grave E., Lample G. (2023). LLaMA: Open and efficient foundation language models (version 1). arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_8_81_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3144139"},{"key":"e_1_3_8_82_1","volume-title":"How AI reduces the world to stereotypes","author":"Turk V.","year":"2023","unstructured":"Turk V. (2023, October 10). How AI reduces the world to stereotypes. Rest of World. https:\/\/restofworld.org\/2023\/ai-image-stereotypes\/"},{"issue":"3","key":"e_1_3_8_83_1","first-page":"1","article-title":"MICE: Multivariate imputation by chained equations in R","volume":"45","author":"van Buuren S.","year":"2011","unstructured":"van Buuren S., Groothuis-Oudshoorn K. (2011). MICE: Multivariate imputation by chained equations in R. Journal of Statistical Software, 45(3), 1\u201367. https:\/\/doi.org\/10.18637\/jss.v045.i03","journal-title":"Journal of Statistical Software"},{"key":"e_1_3_8_84_1","doi-asserted-by":"crossref","unstructured":"Venables W. N. Ripley B. D. (2002). Modern applied statistics with S (4th ed. corr. print). Springer.","DOI":"10.1007\/978-0-387-21706-2"},{"key":"e_1_3_8_85_1","volume-title":"Automated interviewer or augmented survey? Collecting social data with large language models","author":"Villalba A. C.","year":"2023","unstructured":"Villalba A. C., Brown E. M., Scurrell J. V., Entenmann J., Daepp M. I. G. (2023). Automated interviewer or augmented survey? Collecting social data with large language models (arXiv:2309.10187). arXiv. https:\/\/arxiv.org\/abs\/2309.10187"},{"key":"e_1_3_8_86_1","volume-title":"United in diversity? Contextual biases in LLM-based predictions of the 2024 European parliament elections","author":"von der Heyde L.","year":"2025","unstructured":"von der Heyde L., Haensch A.-C., Ma B., Wenz A. (2025). United in diversity? Contextual biases in LLM-based predictions of the 2024 European parliament elections (arXiv: 2409.09045). arXiv. https:\/\/arxiv.org\/abs\/2409.09045"},{"key":"e_1_3_8_87_1","volume-title":"Not all countries celebrate thanksgiving: On the cultural dominance in large language models","author":"Wang W.","year":"2023","unstructured":"Wang W., Jiao W., Huang J., Dai R., Huang J., Tu Z., Lyu M. R. (2023). Not all countries celebrate thanksgiving: On the cultural dominance in large language models (No. arXiv:2310.12481). arXiv. https:\/\/arxiv.org\/abs\/2310.12481"},{"key":"e_1_3_8_88_1","volume-title":"\u201cMy answer is C\u201d: First-token probabilities do not match text answers in instruction-tuned language models","author":"Wang X.","year":"2024","unstructured":"Wang X., Ma B., Hu C., Weber-Genzel L., R\u00f6ttger P., Kreuter F., Hovy D., Plank B. (2024). \u201cMy answer is C\u201d: First-token probabilities do not match text answers in instruction-tuned language models (arXiv:2402.14499). arXiv. https:\/\/arxiv.org\/abs\/2402.14499"},{"key":"e_1_3_8_89_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01686"},{"key":"e_1_3_8_90_1","unstructured":"Wikipedia. (2024). Wikipedia:Wikipedians\u2014Wikipedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Wikipedia:Wikipedians&oldid=1184672006#cite_note-UNU-M-7"},{"key":"e_1_3_8_91_1","doi-asserted-by":"publisher","DOI":"10.1080\/10584609.2020.1785067"},{"key":"e_1_3_8_92_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511818691"},{"key":"e_1_3_8_93_1","unstructured":"W3Techs. (2024). Usage statistics and market share of content languages for websites July 2024. https:\/\/w3techs.com\/technologies\/overview\/content_language"}],"container-title":["Social Science Computer Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08944393251337014","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/08944393251337014","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08944393251337014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:38:20Z","timestamp":1779424700000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/08944393251337014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,26]]},"references-count":92,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1177\/08944393251337014"],"URL":"https:\/\/doi.org\/10.1177\/08944393251337014","relation":{},"ISSN":["0894-4393","1552-8286"],"issn-type":[{"value":"0894-4393","type":"print"},{"value":"1552-8286","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,26]]}}}