{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T06:03:23Z","timestamp":1794377003896,"version":"4.9.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Behav Res"],"DOI":"10.3758\/s13428-025-02868-z","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T22:19:24Z","timestamp":1762381164000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A tutorial on fine-tuning pretrained language models: Applications in social and behavioral science research"],"prefix":"10.3758","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5666-7881","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6194-3913","authenticated-orcid":false,"given":"Wen","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"2868_CR1","doi-asserted-by":"publisher","unstructured":"Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023). Out of one, many: using language models to simulate human samples. Political Analysis, 1\u201315,. https:\/\/doi.org\/10.1017\/pan.2023.2","DOI":"10.1017\/pan.2023.2"},{"key":"2868_CR2","doi-asserted-by":"crossref","unstructured":"Arnold, C., Biedebach, L., Kupfer, A., & Neunhoeffer, M. (2024). The role of hyperparameters in machine learning models and how to tune them. Political Science Research and Methods","DOI":"10.1017\/psrm.2023.61"},{"key":"2868_CR3","doi-asserted-by":"crossref","unstructured":"Ba, Y., Mancenido, M. V., & Pan, R. (2024). Fill in the gaps: Model calibration and generalization with synthetic data. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2024.emnlp-main.955"},{"key":"2868_CR4","doi-asserted-by":"crossref","unstructured":"Bellows-Riecken, K., Mark, R., & Rhodes, R. E. (2013). Qualitative elicitation of affective beliefs related to physical activity. Psychology of Sport and Exercise.","DOI":"10.1016\/j.psychsport.2013.04.002"},{"key":"2868_CR5","doi-asserted-by":"crossref","unstructured":"Boyd, R. L., & , H. A. (2020). Natural language analysis and the psychology of verbal behavior: The past, present, and future states of the field. Journal of Language and Social Psychology","DOI":"10.1177\/0261927X20967028"},{"key":"2868_CR6","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., . . . & Amodei, D. (2020). Language models are few-shot learners. 34th Conference on Neural Information Processing Systems (NeurIPS 2020)."},{"key":"2868_CR7","doi-asserted-by":"crossref","unstructured":"Campos, D. G., Futterer, T., Gfr\u00f6rer, T., Lavelle-Hill, R., Murayama, K., K\u00f6nig, L., Hecht, M., & Scherer, R. (2024). Screening smarter, not harder: A comparative analysis of machine learning screening algorithms and heuristic stopping criteria for systematic reviews in educational research. Educational Psychology Review","DOI":"10.31234\/osf.io\/fpwc2"},{"key":"2868_CR8","doi-asserted-by":"crossref","unstructured":"Chatterjee, A., Gupta, U., Chinnakotla, M. K., Srikanth, R., Galley, M., & Agrawal, P. (2019). Understanding emotions in text using deep learning and big data. Computers in Human Behavior","DOI":"10.1016\/j.chb.2018.12.029"},{"key":"2868_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Lyu, H., Yang, T., Wang, Y., & Luo, J. (2021). Fine-grained analysis of the use of neutral and controversial terms for covid-19 on social media. Social, Cultural, and Behavioral Modeling","DOI":"10.1007\/978-3-030-80387-2_6"},{"key":"2868_CR10","doi-asserted-by":"crossref","unstructured":"Chernikova, O., Stadler, M., Melev, I., & Fischer, F. (2024). Using machine learning for continuous updating of meta-analysis in educational context. Computers in Human Behavior","DOI":"10.1016\/j.chb.2024.108215"},{"key":"2868_CR11","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT, 4171-4186","DOI":"10.18653\/v1\/N19-1423"},{"key":"2868_CR12","doi-asserted-by":"crossref","unstructured":"Feuerriegel, S., Maarouf, A., B\u00e4r, D., Geissler, D., Schweisthal, J., Pr\u00f6llochs, N., ... & Van Bavel, J. J.(2025). Using natural language processing to analyse text data in behavioural science. Nature Reviews Psychology, 4(2), 96\u2013111.","DOI":"10.1038\/s44159-024-00392-z"},{"key":"2868_CR13","doi-asserted-by":"crossref","unstructured":"Gabriel, R. A., Litake, O., Simpson, S., Burton, B. N., Waterman, R. S., & Macias, A. A. (2024). On the development and validation of large language model-based classifiers for identifying social determinants of health. Proceedings of the National Academy of Sciences","DOI":"10.1073\/pnas.2320716121"},{"key":"2868_CR14","doi-asserted-by":"crossref","unstructured":"Gilardi, F., Alizadeh, M., & Kubli, M. (2023). Chatgpt outperforms crowd-workers for text-annotation tasks. Proceedings of the National Academy of Sciences","DOI":"10.1073\/pnas.2305016120"},{"key":"2868_CR15","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. The MIT Press."},{"key":"2868_CR16","doi-asserted-by":"publisher","unstructured":"H\u00e4ffner, S., Hofer, M., Nagl, M., & Walterskirchen, J. (2023). Introducing an interpretable deep learning approach to domain-specific dictionary creation: a use case for conflict prediction. Political Analysis, 1\u201319,. https:\/\/doi.org\/10.1017\/pan.2023.7","DOI":"10.1017\/pan.2023.7"},{"key":"2868_CR17","volume-title":"The elements of statistical learning: Data mining, inference, and prediction","author":"T Hastie","year":"2017","unstructured":"Hastie, T., Tibshirani, R., & Friedman, J. (2017). The elements of statistical learning: Data mining, inference, and prediction. Springer."},{"key":"2868_CR18","doi-asserted-by":"crossref","unstructured":"Hussain, Z., Binz, M., Mata, R., & Wulff, D. U. (2024). A tutorial on open-source large language models for behavioral science. Behavior Research Methods","DOI":"10.31234\/osf.io\/f7stn"},{"key":"2868_CR19","doi-asserted-by":"crossref","unstructured":"Islam, Z., Paul, S., & Rochan, M. (2025). Unsupervised video highlight detection by learning from audio and visual recurrence. 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","DOI":"10.1109\/WACV61041.2025.00843"},{"key":"2868_CR20","doi-asserted-by":"crossref","unstructured":"Jiao, X., Yin, Y., Shang, L., Jiang, X., Chen, X., Li, L., Wang, G., & Liu, Q. (2020). Tinybert: Distilling bert for natural language understanding. EMNLP Findings.","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"2868_CR21","doi-asserted-by":"crossref","unstructured":"Kjell, O., Giorgi, S., & Schwartz, H. A. (2023). The text-package: An r-package for analyzing and visualizing human language using normal language processing and transformers. Psychological Methods","DOI":"10.1037\/met0000542"},{"key":"2868_CR22","doi-asserted-by":"crossref","unstructured":"Kjell, O. N., Kjell, K., & Schwartz, H. A. (2024). Beyond rating scales: With targeted evaluation, large language models are poised for psychological assessment. Psychiatry Research","DOI":"10.31234\/osf.io\/yfd8g"},{"key":"2868_CR23","doi-asserted-by":"crossref","unstructured":"Kjell, O. N. E., Kjell, K., Garcia, D., & Sikstr\u00f6m, S. (2018). Semantic measures: Using natural language processing to measure, differentiate, and describe psychological constructs. Psychological Methods.","DOI":"10.31234\/osf.io\/er6t7"},{"key":"2868_CR24","unstructured":"Kleinberg, B., Van Der Vegt, I., & Mozes, M. (2020). Measuring emotions in the covid-19 real world worry dataset. Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020 ."},{"key":"2868_CR25","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.paid.2016.07.010","volume":"102","author":"PJ Kwantes","year":"2016","unstructured":"Kwantes, P. J., Derbentseva, N., Lam, Q., Vartanian, O., & Marmurek, H. H. (2016). Assessing the big five personality traits with latent semantic analysis. Personality and Individual Differences, 102, 229\u2013233.","journal-title":"Personality and Individual Differences"},{"key":"2868_CR26","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2020). ALBERT: A Lite BERT for self-supervised learning of language representations. ICLR."},{"key":"2868_CR27","doi-asserted-by":"crossref","unstructured":"Laurer, M., van Atteveldt, W., Casas, A., & Welbers, K. (2024). Less annotating, more classifying: Addressing the data scarcity issue of supervised machine learning with deep transfer learning and bert-nli. Political Analysis","DOI":"10.1017\/pan.2023.20"},{"key":"2868_CR28","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"2868_CR29","doi-asserted-by":"crossref","unstructured":"Longpre, S., Wang, Y., & DuBois, C. (2020). how effective is task-agnostic data augmentation for pretrained transformers? Findings of the association for computational linguistics: EMNLP 2020","DOI":"10.18653\/v1\/2020.findings-emnlp.394"},{"key":"2868_CR30","doi-asserted-by":"crossref","unstructured":"Maples, B., Cerit, M., Vishwanath, A., & Pea, R. (2024). Loneliness and suicide mitigation for students using gpt3-enabled chatbots. NPJ Mental Health Research, 3(4)","DOI":"10.1038\/s44184-023-00047-6"},{"key":"2868_CR31","doi-asserted-by":"crossref","unstructured":"Mei, Q., Xie, Y., Yuan, W., & Jackson, M. O. (2024). A turing test of whether ai chatbots are behaviorally similar to humans. Proceedings of the National Academy of Sciences","DOI":"10.2139\/ssrn.4637354"},{"key":"2868_CR32","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. NIPS\u201913: Proceedings of the 26th International Conference on Neural Information Processing Systems"},{"key":"2868_CR33","doi-asserted-by":"crossref","unstructured":"Mu, Y., Wu, B. P., Thorne, W., Robinson, A., Aletras, N., Scarton, C., Bontcheva, k., & Song, X. (2024). Navigating prompt complexity for zero-shot classification: A study of large language models in computational social science. Proceedings Of The 2024 Joint International Conference On Computational Linguistics, Language Resources And Evaluation (Lrec-Coling 2024), 12074\u201312086","DOI":"10.63317\/577de85vh6cz"},{"key":"2868_CR34","doi-asserted-by":"crossref","unstructured":"Nielbo, K. L., Karsdorp, F., Wevers, M., Lassche, A., Baglini, R. B., Kestemont, M., & Tahmasebi, N. (2024). Quantitative text analysis. Nature Reviews Methods Primers, 4, Article 25.","DOI":"10.1038\/s43586-024-00302-w"},{"key":"2868_CR35","doi-asserted-by":"crossref","unstructured":"Pargent, F., Schoedel, R., & Stachl, C. (2023). Best practices in supervised machine learning: A tutorial for psychologists. Advances in Methods and Practices in Psychological Science","DOI":"10.31234\/osf.io\/89snd"},{"key":"2868_CR36","doi-asserted-by":"crossref","unstructured":"Peng, H., Qiu, H. S., Fosse, H. B., & Uzzi, B. (2024). Promotional language and the adoption of innovative ideas in science. Proceedings of the National Academy of Sciences of the United States of America","DOI":"10.1073\/pnas.2320066121"},{"key":"2868_CR37","volume-title":"Linguistic inquiry and word count (liwc): Liwc 2001","author":"JW Pennebaker","year":"2001","unstructured":"Pennebaker, J. W., Francis, M. E., & Booth, R. J. (2001). Linguistic inquiry and word count (liwc): Liwc 2001. Mahwah, NJ: Lawrence Erlbaum Associates."},{"key":"2868_CR38","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1146\/annurev.psych.54.101601.145041","volume":"54","author":"JW Pennebaker","year":"2003","unstructured":"Pennebaker, J. W., Mehl, M. R., & Niederhoffer, K. G. (2003). Psychological aspects of natural language use: our words, our selves. Annual Review of Psychology, 54, 547\u2013577.","journal-title":"Annual Review of Psychology"},{"key":"2868_CR39","doi-asserted-by":"crossref","unstructured":"Rai, S., Stade, E. C., Giorgi, S., Francisco, A., Ungar, L. H., Curtis, B., & Guntuku, S. C. (2024). Key language markers of depression on social media depend on race. Proceedings of the National Academy of Sciences, 121(14), Article e2319837121.","DOI":"10.1073\/pnas.2319837121"},{"key":"2868_CR40","doi-asserted-by":"crossref","unstructured":"Reimers, N., & Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","DOI":"10.18653\/v1\/D19-1410"},{"key":"2868_CR41","unstructured":"Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter. arXiv preprint."},{"key":"2868_CR42","doi-asserted-by":"crossref","unstructured":"Sharma, P., Pradhan, S., & Srivastava, A. (2021). Understanding the luxury purchase intentions of young consumers: A qualitative analysis. Asia-Pacific Journal of Business Administration","DOI":"10.1108\/APJBA-01-2021-0019"},{"key":"2868_CR43","doi-asserted-by":"crossref","unstructured":"Simchon, A., Hadar, B., & Gilead, M. (2023). A computational text analysis investigation of the relation between personal and linguistic agency. Communications Psychology","DOI":"10.31234\/osf.io\/hpwaz"},{"key":"2868_CR44","doi-asserted-by":"publisher","unstructured":"van Buchem, M. M., de Hond, A. A. H., Fanconi, C., Shah, V., Schuessler, M., Kant, I. M. J., Steyerberg, E. W., & Hernandez-Boussard, T. (2024). Applying natural language processing to patient messages to identify depression concerns in cancer patients. Journal of the American Medical Informatics Association, 31(10), 2255-2262. Retrieved from https:\/\/doi.org\/10.1093\/jamia\/ocae188","DOI":"10.1093\/jamia\/ocae188"},{"key":"2868_CR45","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention Is All You Need. 31st Conference on Neural Information Processing Systems."},{"key":"2868_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y. (2023a). On finetuning large language models. Political Analysis","DOI":"10.1017\/pan.2023.36"},{"key":"2868_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y. (2023b). Topic classification for political texts with pretrained language models. Political Analysis","DOI":"10.1017\/pan.2023.3"},{"key":"2868_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Y. (2024). Large language models for depression prediction. Proceedings of the National Academy of Sciences","DOI":"10.1073\/pnas.2409757121"},{"key":"2868_CR49","unstructured":"Wang, Y., Qu, W., & Ye, X. (2024). Selecting between bert and gpt for text classification in political science research. arXiv:2411.05050"},{"key":"2868_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ye, X., Luo, H., & Feng, W. (2025). Large language models for identifying depression concerns in cancer patients. Journal of the American Medical Informatics Association","DOI":"10.1093\/jamia\/ocaf072"},{"key":"2868_CR51","doi-asserted-by":"publisher","DOI":"10.1037\/met0000518","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Tian, J., Yazar, Y., Ones, D. S., & Landers, R. N. (2022). Using natural language processing and machine learning to replace human content coders. Psychological Methods. https:\/\/doi.org\/10.1037\/met0000518","journal-title":"Psychological Methods"},{"key":"2868_CR52","unstructured":"Zhang, X., Lin, J., Mou, X., Yang, S., Liu, X., Sun, L., . . . & Wei, Z. (2025). Socioverse: A world model for social simulation powered by llm agents and a pool of 10 million real-world users. arXiv:2504.10157"},{"key":"2868_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lyu, H., Liu, Y., Zhang, X., Wang, Y., & Luo, J. (2021). Monitoring depression trends on twitter during the covid-19 pandemic: Observational study. JMIR Infodemiology","DOI":"10.2196\/preprints.26769"},{"key":"2868_CR54","unstructured":"Zhong, Q., Ding, L., Liu, J., Du, B., & Tao, D. (2023). Can chatgpt understand too? a comparative study on chatgpt and fine-tuned bert. arXiv:2302.10198 ."},{"key":"2868_CR55","doi-asserted-by":"crossref","unstructured":"Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2024, March). Can large language models transform computational social science? Computational Linguistics, 50(1)","DOI":"10.1162\/coli_a_00502"}],"container-title":["Behavior Research Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3758\/s13428-025-02868-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.3758\/s13428-025-02868-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3758\/s13428-025-02868-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T01:04:50Z","timestamp":1793840690000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.3758\/s13428-025-02868-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":55,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2868"],"URL":"https:\/\/doi.org\/10.3758\/s13428-025-02868-z","relation":{},"ISSN":["1554-3528"],"issn-type":[{"value":"1554-3528","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"assertion":[{"value":"3 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","label":"Competing Interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":4,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The code for the experiments is available at","order":5,"name":"Ethics","label":"Code Availability","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"336"}}