{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T19:30:57Z","timestamp":1772652657643,"version":"3.50.1"},"reference-count":44,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"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":["Int J Artif Intell Educ"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s40593-025-00473-x","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:47:05Z","timestamp":1745516825000},"page":"2372-2398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparing Text Augmentation by GPT-3.5 and Llama3 for Evaluating Student Responses"],"prefix":"10.1016","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0227-7903","authenticated-orcid":false,"given":"Keith","family":"Cochran","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0856-9587","authenticated-orcid":false,"given":"Clayton","family":"Cohn","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0368-7691","authenticated-orcid":false,"given":"Jean Francois","family":"Rouet","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-001X","authenticated-orcid":false,"given":"Peter","family":"Hastings","sequence":"additional","affiliation":[]}],"member":"78","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"473_CR1","unstructured":"Achieve, Inc (2013).Next Generation Science Standards. Washington, D.CNational Academies Press."},{"key":"473_CR2","doi-asserted-by":"crossref","unstructured":"Azevedo, R., Johnson, A., Chauncey, A. Burkett, C. (2010). Self-regulated learning with MetaTutor: Advancing the science of learning with metacognitive tools. New Science Of Learning (pp. 225\u2013247). Springer","DOI":"10.1007\/978-1-4419-5716-0_11"},{"key":"473_CR3","doi-asserted-by":"publisher","unstructured":"Balkus, S.V., Yan, D. (2023). Improving short text classification with augmented data using GPT-3. Natural Language Engineering, pp. 1\u201330. https:\/\/doi.org\/10.1017\/s1351324923000438","DOI":"10.1017\/s1351324923000438"},{"key":"473_CR4","unstructured":"Basu, S., McElhaney, K.W., Rachmatullah, A., Hutchins, N., Biswas, G. Chiu, J. (2022). Promoting computational thinking through science-engineering integration using computational modeling. Proceedings of the 16th International Conference of the Learning Sciences (ICLS)"},{"key":"473_CR5","doi-asserted-by":"crossref","unstructured":"Bayer, M., Kaufhold, M.-A., Buchhold, B., Keller, M., Dallmeyer, J. Reuter, C. (2022). Data augmentation in natural language processing: a novel text generation approach for long and short text classifiers. International Journal of Machine Learning and Cybernetics, pp. 1\u201316","DOI":"10.1007\/s13042-022-01553-3"},{"key":"473_CR6","unstructured":"Bayer, M., Kaufhold, M.-A. Reuter, C. (2021). A survey on data augmentation for text classification. arXiv:2107.03158"},{"issue":"1","key":"473_CR7","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/s40593-015-0057-9","volume":"26","author":"G Biswas","year":"2016","unstructured":"Biswas, G., Segedy, J. R., & Bunchongchit, K. (2016). From design to implementation to practice a learning by teaching system: Betty\u2019s Brain. International Journal of Artificial Intelligence in Education., 26(1), 350\u2013364.","journal-title":"International Journal of Artificial Intelligence in Education."},{"key":"473_CR8","doi-asserted-by":"crossref","unstructured":"Britt, M.A., Rouet, J.-F. Durik, A.M. (2017). Literacy beyond text comprehension: A theory of purposeful reading. Routledge.","DOI":"10.4324\/9781315682860"},{"key":"473_CR9","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., others (2020). Language models are few-shot learners. arXiv:2005.14165"},{"key":"473_CR10","unstructured":"Chen, J., Tam, D., Raffel, C., Bansal, M. Yang, D. (2021). An empirical survey of data augmentation for limited data learning in NLP. Retrieved from arXiv:2106.07499"},{"key":"473_CR11","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.asw.2018.03.004","volume":"37","author":"Y Cho","year":"2018","unstructured":"Cho, Y., & Choi, I. (2018). Writing from sources: Does audience matter? Assessing Writing., 37, 25\u201338.","journal-title":"Assessing Writing."},{"key":"473_CR12","doi-asserted-by":"crossref","unstructured":"Cochran, K., Cohn, C. Hastings, P. (2023). Improving NLP model performance on small educational data sets using self-augmentation. Proceedings of the 15th International Conference on Computer Supported Education","DOI":"10.5220\/0011857200003470"},{"key":"473_CR13","doi-asserted-by":"crossref","unstructured":"Cochran, K., Cohn, C., Hastings, P. Rouet, J.-F. (2023). Improving automated evaluation of student text responses using gpt-3.5 for text data augmentation. Proceedings of the 24th International Conference on Artificial Intelligence in Education (pp. 217\u2013228).","DOI":"10.1007\/978-3-031-36272-9_18"},{"key":"473_CR14","doi-asserted-by":"crossref","unstructured":"Cochran, K., Cohn, C., Hutchins, N., Biswas, G. Hastings, P. (2022). Improving automated evaluation of formative assessments with text data augmentation. International Conference on Artificial Intelligence in Education (pp. 390\u2013401).","DOI":"10.1007\/978-3-031-11644-5_32"},{"key":"473_CR15","unstructured":"Devlin, J., Chang, M.-W., Lee, K. Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"473_CR16","doi-asserted-by":"crossref","unstructured":"Feng, S.Y., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T. Hovy, E. (2021). A survey of data augmentation approaches for nlp. arXiv:2105.03075","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"473_CR17","doi-asserted-by":"publisher","unstructured":"Geden, M., Emerson, A., Carpenter, D., Rowe, J., Azevedo, R., & Lester, J. (2021). Predictive student modeling in game-based learning environments with word embedding representations of reflection. International Journal of Artificial Intelligence in Education, 31,. https:\/\/doi.org\/10.1007\/s40593-020-00220-4","DOI":"10.1007\/s40593-020-00220-4"},{"key":"473_CR18","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D. Smith, N.A. (2020). Don\u2019t stop pretraining: adapt language models to domains and tasks. arXiv:2004.10964","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"473_CR19","doi-asserted-by":"crossref","unstructured":"Hastings, P., Hughes, S., Britt, A., Blaum, D. Wallace, P. (2014). Toward automatic inference of causal structure in student essays. International Conference on Intelligent Tutoring Systems, (pp. 266\u2013271)","DOI":"10.1007\/978-3-319-07221-0_33"},{"key":"473_CR20","unstructured":"HuggingFace (n.d). (2024). jeveuxaider\/activity-classifier. jeveuxaider\/activity-classifier. https:\/\/huggingface.co\/jeveuxaider\/activity-classifier"},{"key":"473_CR21","unstructured":"Hutchins, N.M., Basu, S., McElhaney, K.W., Chiu, J.L., Fick, S.J., Zhang, N., Biswas, G. (2021). Coherence across conceptual and computational representations of students- scientific models. Proceedings of the 15th International Conference of the Learning Sciences-ICLS 2021"},{"issue":"3","key":"473_CR22","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/s40593-020-00199-y","volume":"30","author":"T K\u00e4ser","year":"2020","unstructured":"K\u00e4ser, T., & Schwartz, D. L. (2020). Modeling and analyzing inquiry strategies in open-ended - learning environments. International Journal of Artificial Intelligence in Education, 30(3), 504\u2013535.","journal-title":"International Journal of Artificial Intelligence in Education"},{"issue":"3","key":"473_CR23","doi-asserted-by":"publisher","first-page":"14219","DOI":"10.48084\/etasr.7200","volume":"14","author":"A Kumar","year":"2024","unstructured":"Kumar, A., Sharma, R., & Bedi, P. (2024). Towards optimal nlp solutions: Analyzing gpt and llama-2 models across model scale, dataset size, and task diversity. Engineering, Technology & Applied Science Research, 14(3), 14219\u201314224.","journal-title":"Engineering, Technology & Applied Science Research"},{"issue":"3","key":"473_CR24","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.3390\/make5030059","volume":"5","author":"T Kuzman","year":"2023","unstructured":"Kuzman, T., Mozeti\u010d, I., & Ljube\u0161i\u0107, N. (2023). Automatic Genre Identification for Robust Enrichment of Massive Text Collections: Investigation of Classification Methods in the Era of Large Language Models. Machine Learning and Knowledge Extraction, 5(3), 1149\u20131175.","journal-title":"Machine Learning and Knowledge Extraction"},{"key":"473_CR25","doi-asserted-by":"crossref","unstructured":"Liu, P., Wang, X., Xiang, C. Meng, W. (2020). A survey of text data augmentation A survey of text data augmentation. 2020 International Conference on Computer Communication and Network Security (CCNS) (pp. 191\u2013195).","DOI":"10.1109\/CCNS50731.2020.00049"},{"issue":"1","key":"473_CR26","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/s40593-015-0072-x","volume":"26","author":"R Luckin","year":"2016","unstructured":"Luckin, R., & du Boulay, B. (2016). Reflections on the Ecolab and the Zone of Proximal Development. International Journal of Artificial Intelligence in Education, 26(1), 416\u2013430.","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"473_CR27","unstructured":"McElhaney, K.W., Zhang, N., Basu, S., McBride, E., Biswas, G., Chiu, J. (2020). Using computational modeling to integrate science and engineering curricular activities. M. Gresalfi & I. Horn (Eds.), The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS) 2020 (vol. 3)"},{"key":"473_CR28","unstructured":"Meta (n.d). (2024). Introducing Meta Llama 3: The most capable openly available LLM to date. https:\/\/ai.meta.com\/blog\/meta-llama-3\/"},{"key":"473_CR29","doi-asserted-by":"crossref","unstructured":"OECD (2021). 21st-century readers. PISA, OECD Publishing. https:\/\/www.oecd-ilibrary.org\/content\/publication\/a83d84cb-en","DOI":"10.1787\/a83d84cb-en"},{"key":"473_CR30","unstructured":"Piedboeuf, F., Langlais, P. (2024). Data augmentation is dead, long live data augmentation. arXiv:2402.14895"},{"key":"473_CR31","doi-asserted-by":"crossref","unstructured":"Quteineh, H., Samothrakis, S., Sutcliffe, R. (2020). Textual data augmentation for efficient active learning on tiny datasets. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 7400\u20137410)","DOI":"10.18653\/v1\/2020.emnlp-main.600"},{"key":"473_CR32","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Stanovsky, G. (2022). On the limitations of dataset balancing: The lost battle against spurious correlations. arXiv:2204.12708","DOI":"10.18653\/v1\/2022.findings-naacl.168"},{"key":"473_CR33","doi-asserted-by":"publisher","unstructured":"Seo, J.-W., Jung, H.-G., & Lee, S.-W. (2021). Self-augmentation: Generalizing deep networks to unseen classes for few-shot learning. Neural Networks., 138, 140\u2013149. https:\/\/doi.org\/10.1016\/j.neunet.2021.02.007 Retrieved fromhttps:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608021000496","DOI":"10.1016\/j.neunet.2021.02.007"},{"issue":"1","key":"473_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data., 6(1), 1\u201348.","journal-title":"Journal of Big Data."},{"issue":"1","key":"473_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00492-0","volume":"8","author":"C Shorten","year":"2021","unstructured":"Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021). Text data augmentation for deep learning. Journal of big Data., 8(1), 1\u201334.","journal-title":"Journal of big Data."},{"key":"473_CR36","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., . . . others (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"issue":"3","key":"473_CR37","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1037\/0022-0663.93.3.521","volume":"93","author":"P van den Broek","year":"2001","unstructured":"van den Broek, P., Tzeng, Y., Risden, K., Trabasso, T., & Basche, P. (2001). Inferential questioning: Effects on comprehension of narrative texts as a function of grade and timing. Journal of Educational Psychology., 93(3), 521.","journal-title":"Journal of Educational Psychology."},{"key":"473_CR38","first-page":"5776","volume":"33","author":"W Wang","year":"2020","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., & Zhou, M. (2020). Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, 33, 5776\u20135788.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"473_CR39","unstructured":"Wikipedia (n.d). (2024). GPT-3. Gpt-3. https:\/\/en.wikipedia.org\/wiki\/GPT-3"},{"key":"473_CR40","doi-asserted-by":"crossref","unstructured":"Winne, P.H., Hadwin, A.F. (2013). nStudy: Tracing and supporting self-regulated learning in the internet. International handbook of metacognition and learning technologies (pp. 293\u2013308). Springer.","DOI":"10.1007\/978-1-4419-5546-3_20"},{"key":"473_CR41","doi-asserted-by":"crossref","unstructured":"Wu, L., Xie, P., Zhou, J., Zhang, M., Ma, C., Xu, G., Zhang, M. (2022). Self-augmentation for named entity recognition with meta reweighting. arXiv:2204.11406","DOI":"10.18653\/v1\/2022.naacl-main.297"},{"key":"473_CR42","doi-asserted-by":"crossref","unstructured":"Xia, C., Zhang, C., Zhang, J., Liang, T., Peng, H., Philip, S.Y. (2020). Low-shot learning in natural language processing. 2020 IEEE Second International Conference on Cognitive Machine Intelligence (CogMI) (pp. 185\u2013189).","DOI":"10.1109\/CogMI50398.2020.00031"},{"key":"473_CR43","unstructured":"Yogatama, D., d\u2019Autume, C.d.M., Connor, J., Kocisky, T., Chrzanowski, M., Kong, L., . . . others (2019). Learning and evaluating general linguistic intelligence. arXiv preprint arXiv:1901.11373"},{"key":"473_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, N., Biswas, G., McElhaney, K.W., Basu, S., McBride, E., Chiu, J.L. (2020). Studying the interactions between science, engineering, and computational thinking in a learning-by-modeling environment. International Conference on Artificial Intelligence in Education (pp. 598\u2013609).","DOI":"10.1007\/978-3-030-52237-7_48"}],"container-title":["International Journal of Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-025-00473-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40593-025-00473-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-025-00473-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:12:40Z","timestamp":1772647960000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40593-025-00473-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["473"],"URL":"https:\/\/doi.org\/10.1007\/s40593-025-00473-x","relation":{},"ISSN":["1560-4292","1560-4306"],"issn-type":[{"value":"1560-4292","type":"print"},{"value":"1560-4306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]},"assertion":[{"value":"31 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2025","order":2,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}