{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:15:57Z","timestamp":1792782957222,"version":"4.5.0"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62077030"],"award-info":[{"award-number":["62077030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62107022"],"award-info":[{"award-number":["62107022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of China","doi-asserted-by":"publisher","award":["21YJC880037"],"award-info":[{"award-number":["21YJC880037"]}],"id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research and Innovation Projects of Jiangsu Province","award":["KYCX22_2726"],"award-info":[{"award-number":["KYCX22_2726"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Educ Inf Technol"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s10639-024-12851-4","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T06:01:58Z","timestamp":1721196118000},"page":"2331-2360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Evaluating the quality of student-generated content in learnersourcing: A large language model based approach"],"prefix":"10.1007","volume":"30","author":[{"given":"Kangkang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyang","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianmin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"issue":"1","key":"12851_CR1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/TLT.2021.3058644","volume":"14","author":"S Abdi","year":"2021","unstructured":"Abdi, S., Khosravi, H., Sadiq, S., & Demartini, G. (2021). Evaluating the Quality of Learning Resources: A Learnersourcing Approach. IEEE Transactions on Learning Technologies, 14(1), 81\u201392. https:\/\/doi.org\/10.1109\/TLT.2021.3058644","journal-title":"IEEE Transactions on Learning Technologies"},{"key":"12851_CR2","doi-asserted-by":"publisher","unstructured":"Adline, A. L. A., & Mahalakshmi, G. S. (2011). A novel framework for E-learning content evaluation. In 2011 Third International Conference on Advanced Computing (pp. 346\u2013352). https:\/\/doi.org\/10.1109\/ICoAC.2011.6165200.","DOI":"10.1109\/ICoAC.2011.6165200"},{"key":"12851_CR3","doi-asserted-by":"publisher","unstructured":"Altamimi, A. B. (2023). Effectiveness of ChatGPT in Essay Autograding. In 2023 International Conference on Computing, Electronics & Communications Engineering (iCCECE) (pp. 102\u2013106). https:\/\/doi.org\/10.1109\/iCCECE59400.2023.10238541.","DOI":"10.1109\/iCCECE59400.2023.10238541"},{"issue":"4","key":"12851_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3484828","volume":"13","author":"G Amaral","year":"2021","unstructured":"Amaral, G., Piscopo, A., Kaffee, L. A., Rodrigues, O., & Simperl, E. (2021). Assessing the quality of sources in Wikidata across languages: A hybrid approach. Journal of Data and Information Quality (JDIQ), 13(4), 1\u201335. https:\/\/doi.org\/10.1145\/3484828","journal-title":"Journal of Data and Information Quality (JDIQ)"},{"key":"12851_CR5","doi-asserted-by":"publisher","first-page":"118534","DOI":"10.1016\/j.eswa.2022.118534","volume":"213","author":"I Ameer","year":"2023","unstructured":"Ameer, I., B\u00f6l\u00fcc\u00fc, N., Siddiqui, M. H. F., Can, B., Sidorov, G., & Gelbukh, A. (2023). Multi-label emotion classification in texts using transfer learning. Expert Systems with Applications, 213, 118534. https:\/\/doi.org\/10.1016\/j.eswa.2022.118534","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"12851_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s41239-019-0140-7","volume":"16","author":"R Arruabarrena","year":"2019","unstructured":"Arruabarrena, R., S\u00e1nchez, A., Blanco, J. M., Vadillo, J. A., & Usandizaga, I. (2019). Integration of good practices of active methodologies with the reuse of student-generated content. International Journal of Educational Technology in Higher Education, 16(1), 10. https:\/\/doi.org\/10.1186\/s41239-019-0140-7","journal-title":"International Journal of Educational Technology in Higher Education"},{"key":"12851_CR7","doi-asserted-by":"crossref","unstructured":"Azaiz, I., Kiesler, N., & Strickroth, S. (2024). Feedback-Generation for Programming Exercises With GPT-4. arXiv preprint arXiv:2403.04449.","DOI":"10.1145\/3649217.3653594"},{"issue":"1","key":"12851_CR8","doi-asserted-by":"publisher","first-page":"52","DOI":"10.61969\/jai.1337500","volume":"7","author":"D Baidoo-anu","year":"2023","unstructured":"Baidoo-anu, D., & Owusu Ansah, L. (2023). Education in the Era of Generative Artificial Intelligence (AI): Understanding the Potential Benefits of ChatGPT in Promoting Teaching and Learning. Journal of AI, 7(1), 52\u201362. https:\/\/doi.org\/10.61969\/jai.1337500","journal-title":"Journal of AI"},{"key":"12851_CR9","doi-asserted-by":"crossref","unstructured":"Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Gianinazzi, L., Gajda, J., et al. (2023). Graph of Thoughts: Solving Elaborate Problems with Large Language Models. arXiv preprint arXiv:2308.09687.","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"12851_CR10","doi-asserted-by":"publisher","first-page":"100177","DOI":"10.1016\/j.caeai.2023.100177","volume":"5","author":"A Bewersdorff","year":"2023","unstructured":"Bewersdorff, A., Se\u00dfler, K., Baur, A., Kasneci, E., & Nerdel, C. (2023). Assessing student errors in experimentation using artificial intelligence and large language models: A comparative study with human raters. Computers and Education: Artificial Intelligence, 5, 100177. https:\/\/doi.org\/10.1016\/j.caeai.2023.100177","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"12851_CR11","doi-asserted-by":"publisher","unstructured":"Bhatnagar, S., Zouaq, A., Desmarais, M. C., & Charles, E. (2020). Learnersourcing quality assessment of explanations for peer instruction. In Addressing Global Challenges and Quality Education: 15th European Conference on Technology Enhanced Learning, Proceedings 15 (pp. 144\u2013157). https:\/\/doi.org\/10.1007\/978-3-030-57717-9_11.","DOI":"10.1007\/978-3-030-57717-9_11"},{"key":"12851_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, R., Jiang, H., Shi, S., & Xu, R. (2023). Exploring the use of large language models for reference-free text quality evaluation: A preliminary empirical study. arXiv preprint arXiv:2304.00723.","DOI":"10.18653\/v1\/2023.findings-ijcnlp.32"},{"key":"12851_CR13","doi-asserted-by":"publisher","unstructured":"Cheng, Z., Ding, Y., Zhu, L., & Kankanhalli, M. (2018). Aspect-aware latent factor model: Rating prediction with ratings and reviews. In Proceedings of the 2018 world wide web conference (pp. 639\u2013648). https:\/\/doi.org\/10.1145\/3178876.3186145.","DOI":"10.1145\/3178876.3186145"},{"key":"12851_CR14","doi-asserted-by":"crossref","unstructured":"Chiang, C.-H., & Lee, H. (2023). Can Large Language Models Be an Alternative to Human Evaluations? arXiv preprint arXiv:2305.01937.","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"12851_CR15","doi-asserted-by":"publisher","unstructured":"Dang, Q.-V., & Ignat, C.-L. (2016). Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia. In 2016 IEEE 2nd International Conference on Collaboration and Internet Computing (CIC) (pp. 266\u2013275). https:\/\/doi.org\/10.1109\/CIC.2016.044.","DOI":"10.1109\/CIC.2016.044"},{"issue":"1","key":"12851_CR16","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/TLT.2022.3229022","volume":"16","author":"A Darvishi","year":"2023","unstructured":"Darvishi, A., Khosravi, H., Rahimi, A., Sadiq, S., & Ga\u0161evi\u0107, D. (2023). Assessing the Quality of Student-Generated Content at Scale: A Comparative Analysis of Peer-Review Models. IEEE Transactions on Learning Technologies, 16(1), 106\u2013120. https:\/\/doi.org\/10.1109\/TLT.2022.3229022","journal-title":"IEEE Transactions on Learning Technologies"},{"key":"12851_CR17","doi-asserted-by":"publisher","unstructured":"Doroudi, S., Williams, J., Kim, J., Patikorn, T., Ostrow, K., Selent, D., et al. (2018). Crowdsourcing and education: Towards a theory and praxis of learnersourcing. International Society of the Learning Sciences, Inc.[ISLS]. https:\/\/doi.org\/10.22318\/cscl2018.1267.","DOI":"10.22318\/cscl2018.1267"},{"issue":"2","key":"12851_CR18","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s11135-014-0003-1","volume":"49","author":"R Falotico","year":"2015","unstructured":"Falotico, R., & Quatto, P. (2015). Fleiss\u2019 kappa statistic without paradoxes. Quality & Quantity, 49(2), 463\u2013470. https:\/\/doi.org\/10.1007\/s11135-014-0003-1","journal-title":"Quality & Quantity"},{"key":"12851_CR19","unstructured":"Gao, M., Ruan, J., Sun, R., Yin, X., Yang, S., & Wan, X. (2023). Human-like summarization evaluation with chatgpt. arXiv preprint arXiv:2304.02554."},{"issue":"7","key":"12851_CR20","doi-asserted-by":"publisher","first-page":"692","DOI":"10.3390\/educsci13070692","volume":"13","author":"S Grassini","year":"2023","unstructured":"Grassini, S. (2023). Shaping the Future of Education: Exploring the Potential and Consequences of AI and ChatGPT in Educational Settings. Education Sciences, 13(7), 692. https:\/\/doi.org\/10.3390\/educsci13070692","journal-title":"Education Sciences"},{"key":"12851_CR21","doi-asserted-by":"publisher","unstructured":"Gu, K., & Budhkar, A. (2021). A Package for Learning on Tabular and Text Data with Transformers. In A. Zadeh, L.-P. Morency, P. P. Liang, C. Ross, R. Salakhutdinov, S. Poria, et al. (Eds.), Proceedings of the Third Workshop on Multimodal Artificial Intelligence (pp. 69\u201373). https:\/\/doi.org\/10.18653\/v1\/2021.maiworkshop-1.10.","DOI":"10.18653\/v1\/2021.maiworkshop-1.10"},{"key":"12851_CR22","unstructured":"Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., et al. (2023). How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597."},{"key":"12851_CR23","doi-asserted-by":"publisher","unstructured":"Guo, Q., Cao, J., Xie, X., Liu, S., Li, X., Chen, B., & Peng, X. (2024). Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study. In Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering (pp. 1\u201313). https:\/\/doi.org\/10.1145\/3597503.3623306.","DOI":"10.1145\/3597503.3623306"},{"key":"12851_CR24","unstructured":"Han, J., Yoo, H., Myung, J., Kim, M., Lim, H., Kim, Y., ... & Oh, A. (2023). Fabric: Automated scoring and feedback generation for essays. arXiv preprint arXiv:2310.05191."},{"key":"12851_CR25","doi-asserted-by":"publisher","first-page":"220922","DOI":"10.1109\/ACCESS.2020.3043291","volume":"8","author":"Y Han","year":"2020","unstructured":"Han, Y., Wu, W., Yan, Y., & Zhang, L. (2020). Human-Machine Hybrid Peer Grading in SPOCs. IEEE Access, 8, 220922\u2013220934. https:\/\/doi.org\/10.1109\/ACCESS.2020.3043291","journal-title":"IEEE Access"},{"issue":"13","key":"12851_CR26","doi-asserted-by":"publisher","first-page":"2180","DOI":"10.1080\/09500693.2014.916831","volume":"36","author":"J Hardy","year":"2014","unstructured":"Hardy, J., Bates, S. P., Casey, M. M., Galloway, K. W., Galloway, R. K., Kay, A. E., et al. (2014). Student-Generated Content: Enhancing learning through sharing multiple-choice questions. International Journal of Science Education, 36(13), 2180\u20132194. https:\/\/doi.org\/10.1080\/09500693.2014.916831","journal-title":"International Journal of Science Education"},{"key":"12851_CR27","doi-asserted-by":"publisher","unstructured":"Hasan Dalip, D., Andr\u00e9 Gon\u00e7alves, M., Cristo, M., & Calado, P. (2009). Automatic quality assessment of content created collaboratively by web communities: a case study of wikipedia. In Proceedings of the 9th ACM\/IEEE-CS joint conference on Digital libraries (pp. 295\u2013304). https:\/\/doi.org\/10.1145\/1555400.1555449.","DOI":"10.1145\/1555400.1555449"},{"issue":"2","key":"12851_CR28","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2478\/v10117-011-0021-1","volume":"30","author":"J Hauke","year":"2011","unstructured":"Hauke, J., & Kossowski, T. (2011). Comparison of Values of Pearson\u2019s and Spearman\u2019s Correlation Coefficients on the Same Sets of Data. Quaestiones Geographicae, 30(2), 87\u201393. https:\/\/doi.org\/10.2478\/v10117-011-0021-1","journal-title":"Quaestiones Geographicae"},{"key":"12851_CR29","first-page":"176","volume":"2","author":"JR Hayes","year":"1987","unstructured":"Hayes, J. R., Flower, L., Schriver, K. A., Stratman, J., Carey, L., et al. (1987). Cognitive processes in revision. Advances in Applied Psycholinguistics, 2, 176\u2013240.","journal-title":"Advances in Applied Psycholinguistics"},{"key":"12851_CR30","doi-asserted-by":"publisher","unstructured":"Iqbal, M., Laili Udhiah, R., Rana Nugraha, T., & Pao, H.-K. (2023). ASAGeR: Automated Short Answer Grading Regressor via Sentence Simplification. In 2023 IEEE International Conference on Knowledge Graph (ICKG) (pp. 60\u201368). https:\/\/doi.org\/10.1109\/ICKG59574.2023.00013","DOI":"10.1109\/ICKG59574.2023.00013"},{"key":"12851_CR31","volume-title":"ISO\/IEC 23126:2021(en) Information technology for learning, education and training \u2014 Ubiquitous learning resource organization and description framework","author":"ISO\/IEC","year":"2021","unstructured":"ISO\/IEC. (2021). ISO\/IEC 23126:2021(en) Information technology for learning, education and training \u2014 Ubiquitous learning resource organization and description framework."},{"key":"12851_CR32","doi-asserted-by":"publisher","unstructured":"Iwane, N., Gao, C., & Yoshida, M. (2013). Question Generation for Learner Centered Learning. In 2013 IEEE 13th International Conference on Advanced Learning Technologies (pp. 330\u2013332). https:\/\/doi.org\/10.1109\/ICALT.2013.102.","DOI":"10.1109\/ICALT.2013.102"},{"key":"12851_CR33","doi-asserted-by":"publisher","unstructured":"Jiang, T., Zhang, P., Lu, T., & Gu, N. (2022). Predicting Rollback Edits on Stack Overflow Based on Deep Fusion of Metadata and Text. In 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD) (pp. 377\u2013382). https:\/\/doi.org\/10.1109\/CSCWD54268.2022.9776034.","DOI":"10.1109\/CSCWD54268.2022.9776034"},{"key":"12851_CR34","doi-asserted-by":"publisher","first-page":"100151","DOI":"10.1016\/j.caeai.2023.100151","volume":"5","author":"H Khosravi","year":"2023","unstructured":"Khosravi, H., Denny, P., Moore, S., & Stamper, J. (2023). Learnersourcing in the age of AI: Student, educator and machine partnerships for content creation. Computers and Education: Artificial Intelligence, 5, 100151. https:\/\/doi.org\/10.1016\/j.caeai.2023.100151","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"12851_CR35","unstructured":"Kim, G., Baldi, P., & McAleer, S. (2024). Language models can solve computer tasks. Advances in Neural Information Processing Systems, 36."},{"key":"12851_CR36","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199\u201322213.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"12851_CR37","doi-asserted-by":"publisher","unstructured":"Kumar, V., & Boulanger, D. (2020). Explainable automated essay scoring: Deep learning really has pedagogical value. In Frontiers in education (Vol. 5, p. 572367). https:\/\/doi.org\/10.3389\/feduc.2020.572367.","DOI":"10.3389\/feduc.2020.572367"},{"key":"12851_CR38","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.chb.2013.06.047","volume":"30","author":"E Kurilovas","year":"2014","unstructured":"Kurilovas, E., Serikoviene, S., & Vuorikari, R. (2014). Expert centred vs learner centred approach for evaluating quality and reusability of learning objects. Computers in Human Behavior, 30, 526\u2013534. https:\/\/doi.org\/10.1016\/j.chb.2013.06.047","journal-title":"Computers in Human Behavior"},{"issue":"1","key":"12851_CR39","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1111\/jcal.12729","volume":"39","author":"H Lahza","year":"2023","unstructured":"Lahza, H., Khosravi, H., & Demartini, G. (2023). Analytics of learning tactics and strategies in an online learnersourcing environment. Journal of Computer Assisted Learning, 39(1), 94\u2013112. https:\/\/doi.org\/10.1111\/jcal.12729","journal-title":"Journal of Computer Assisted Learning"},{"key":"12851_CR40","doi-asserted-by":"publisher","first-page":"101742","DOI":"10.1016\/j.is.2021.101742","volume":"99","author":"C-H Lai","year":"2021","unstructured":"Lai, C.-H., & Hsu, C.-Y. (2021). Rating prediction based on combination of review mining and user preference analysis. Information Systems, 99, 101742. https:\/\/doi.org\/10.1016\/j.is.2021.101742","journal-title":"Information Systems"},{"key":"12851_CR41","doi-asserted-by":"publisher","first-page":"100210","DOI":"10.1016\/j.caeai.2024.100210","volume":"6","author":"E Latif","year":"2024","unstructured":"Latif, E., & Zhai, X. (2024). Fine-tuning ChatGPT for automatic scoring. Computers and Education: Artificial Intelligence, 6, 100210. https:\/\/doi.org\/10.1016\/j.caeai.2024.100210","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"12851_CR42","doi-asserted-by":"crossref","unstructured":"Latif, E., Fang, L., Ma, P., & Zhai, X. (2023). Knowledge distillation of LLM for automatic scoring of science education assessments. arXiv preprint arXiv:2312.15842.","DOI":"10.1007\/978-3-031-64312-5_20"},{"key":"12851_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-023-12249-8","author":"U Lee","year":"2023","unstructured":"Lee, U., Jung, H., Jeon, Y., Sohn, Y., Hwang, W., Moon, J., & Kim, H. (2023). Few-shot is enough: Exploring ChatGPT prompt engineering method for automatic question generation in english education. Education and Information Technologies. https:\/\/doi.org\/10.1007\/s10639-023-12249-8","journal-title":"Education and Information Technologies"},{"key":"12851_CR44","doi-asserted-by":"publisher","first-page":"100213","DOI":"10.1016\/j.caeai.2024.100213","volume":"6","author":"G-G Lee","year":"2024","unstructured":"Lee, G.-G., Latif, E., Wu, X., Liu, N., & Zhai, X. (2024). Applying large language models and chain-of-thought for automatic scoring. Computers and Education: Artificial Intelligence, 6, 100213. https:\/\/doi.org\/10.1016\/j.caeai.2024.100213","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"12851_CR45","unstructured":"Levonian, Z., Li, C., Zhu, W., Gade, A., Henkel, O., Postle, M. E., & Xing, W. (2023). Retrieval-augmented generation to improve math question-answering: Trade-offs between groundedness and human preference. arXiv preprint arXiv:2310.03184."},{"key":"12851_CR46","doi-asserted-by":"publisher","unstructured":"Li, L., Zhang, L., Wang, A., & Huang, K. (2020). Investigating Factors for Assessing the Quality of Academic User-Generated Content on Social Media. In Proceedings of the ACM\/IEEE Joint Conference on Digital Libraries in 2020 (pp. 511\u2013512). https:\/\/doi.org\/10.1145\/3383583.3398588.","DOI":"10.1145\/3383583.3398588"},{"key":"12851_CR47","doi-asserted-by":"crossref","unstructured":"Li, J., Gui, L., Zhou, Y., West, D., Aloisi, C., & He, Y. (2023). Distilling ChatGPT for Explainable Automated Student Answer Assessment. arXiv preprint arXiv:2305.12962.","DOI":"10.18653\/v1\/2023.findings-emnlp.399"},{"key":"12851_CR48","doi-asserted-by":"publisher","unstructured":"Liu, Z., He, X., Liu, L., Liu, T., & Zhai, X. (2023). Context Matters: A Strategy to Pre-train Language Model for Science Education (Vol. 1831, pp. 666\u2013674). https:\/\/doi.org\/10.1007\/978-3-031-36336-8_103.","DOI":"10.1007\/978-3-031-36336-8_103"},{"key":"12851_CR49","unstructured":"Liu, Y., Singh, A., Freeman, C. D., Co-Reyes, J. D., & Liu, P. J. (2023). Improving large language model fine-tuning for solving math problems. arXiv preprint arXiv:2310.10047."},{"key":"12851_CR50","unstructured":"Luo, Z., Xie, Q., & Ananiadou, S. (2023). Chatgpt as a factual inconsistency evaluator for abstractive text summarization. arXiv preprint arXiv:2303.15621."},{"issue":"6","key":"12851_CR51","doi-asserted-by":"publisher","first-page":"102","DOI":"10.14742\/ajet.6735","volume":"37","author":"A McDonald","year":"2021","unstructured":"McDonald, A., McGowan, H., Dollinger, M., Naylor, R., & Khosravi, H. (2021). Repositioning students as co-creators of curriculum for online learning resources. Australasian Journal of Educational Technology, 37(6), 102\u2013118. https:\/\/doi.org\/10.14742\/ajet.6735","journal-title":"Australasian Journal of Educational Technology"},{"issue":"1","key":"12851_CR52","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1609\/icwsm.v4i1.14019","volume":"4","author":"M McGlohon","year":"2010","unstructured":"McGlohon, M., Glance, N., & Reiter, Z. (2010). Star Quality: Aggregating Reviews to Rank Products and Merchants. Proceedings of the International AAAI Conference on Web and Social Media, 4(1), 114\u2013121. https:\/\/doi.org\/10.1609\/icwsm.v4i1.14019","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media"},{"issue":"2","key":"12851_CR53","doi-asserted-by":"publisher","first-page":"100050","DOI":"10.1016\/j.rmal.2023.100050","volume":"2","author":"A Mizumoto","year":"2023","unstructured":"Mizumoto, A., & Eguchi, M. (2023). Exploring the potential of using an AI language model for automated essay scoring. Research Methods in Applied Linguistics, 2(2), 100050. https:\/\/doi.org\/10.1016\/j.rmal.2023.100050","journal-title":"Research Methods in Applied Linguistics"},{"issue":"3","key":"12851_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2811282","volume":"48","author":"E Momeni","year":"2015","unstructured":"Momeni, E., Cardie, C., & Diakopoulos, N. (2015). A survey on assessment and ranking methodologies for user-generated content on the web. ACM Computing Surveys (CSUR), 48(3), 1\u201349. https:\/\/doi.org\/10.1145\/2811282","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"12851_CR55","doi-asserted-by":"publisher","unstructured":"Moore, S., Stamper, J., Brooks, C., Denny, P., & Khosravi, H. (2022). Learnersourcing: Student-generated Content @ Scale. In Proceedings of the Ninth ACM Conference on Learning @ Scale (pp. 259\u2013262). https:\/\/doi.org\/10.1145\/3491140.3528286.","DOI":"10.1145\/3491140.3528286"},{"key":"12851_CR56","doi-asserted-by":"publisher","unstructured":"Moore, S., Nguyen, H. A., Chen, T., & Stamper, J. (2023). Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods. In O. Viberg, I. Jivet, P. J. Mu\u00f1oz-Merino, M. Perifanou, & T. Papathoma (Eds.), Responsive and Sustainable Educational Futures (pp. 229\u2013245). https:\/\/doi.org\/10.1007\/978-3-031-42682-7_16.","DOI":"10.1007\/978-3-031-42682-7_16"},{"key":"12851_CR57","unstructured":"OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., ... & McGrew, B. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774."},{"issue":"1","key":"12851_CR58","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1007\/s10639-022-11151-z","volume":"28","author":"P Ren","year":"2023","unstructured":"Ren, P., Yang, L., & Luo, F. (2023). Automatic scoring of student feedback for teaching evaluation based on aspect-level sentiment analysis. Education and Information Technologies, 28(1), 797\u2013814. https:\/\/doi.org\/10.1007\/s10639-022-11151-z","journal-title":"Education and Information Technologies"},{"key":"12851_CR59","doi-asserted-by":"publisher","first-page":"115111","DOI":"10.1016\/j.eswa.2021.115111","volume":"181","author":"S Sadiq","year":"2021","unstructured":"Sadiq, S., Umer, M., Ullah, S., Mirjalili, S., Rupapara, V., & Nappi, M. (2021). Discrepancy detection between actual user reviews and numeric ratings of Google App store using deep learning. Expert Systems with Applications, 181, 115111. https:\/\/doi.org\/10.1016\/j.eswa.2021.115111","journal-title":"Expert Systems with Applications"},{"key":"12851_CR60","doi-asserted-by":"publisher","unstructured":"Schmidt, M., & Zangerle, E. (2019). Article quality classification on Wikipedia: introducing document embeddings and content features. In Proceedings of the 15th International Symposium on Open Collaboration (pp. 1\u20138). https:\/\/doi.org\/10.1145\/3306446.3340831.","DOI":"10.1145\/3306446.3340831"},{"key":"12851_CR61","doi-asserted-by":"crossref","unstructured":"Schneider, J., Schenk, B., Niklaus, C., & Vlachos, M. (2023). Towards llm-based autograding for short textual answers. arXiv preprint arXiv:2309.11508.","DOI":"10.5220\/0012552200003693"},{"issue":"4","key":"12851_CR62","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1109\/47.44536","volume":"32","author":"KA Schriver","year":"1989","unstructured":"Schriver, K. A. (1989). Evaluating text quality: The continuum from text-focused to reader-focused methods. IEEE Transactions on Professional Communication, 32(4), 238\u2013255.","journal-title":"IEEE Transactions on Professional Communication"},{"issue":"4","key":"12851_CR63","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1037\/h0092690","volume":"89","author":"BA Shearer","year":"1997","unstructured":"Shearer, B. A., Lundeberg, M. A., & Coballes-Vega, C. (1997). Making the connection between research and reality: Strategies teachers use to read and evaluate journal articles. Journal of Educational Psychology, 89(4), 592\u2013598. https:\/\/doi.org\/10.1037\/h0092690","journal-title":"Journal of Educational Psychology"},{"key":"12851_CR64","doi-asserted-by":"publisher","unstructured":"Shen, C., Cheng, L., Nguyen, X.-P., You, Y., & Bing, L. (2023). Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization. In H. Bouamor, J. Pino, & K. Bali (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 4215\u20134233). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.278.","DOI":"10.18653\/v1\/2023.findings-emnlp.278"},{"key":"12851_CR65","unstructured":"Shi, X., Mueller, J., Erickson, N., Li, M., & Smola, A. J. (2021). Benchmarking multimodal automl for tabular data with text fields. arXiv preprint arXiv:2111.02705."},{"key":"12851_CR66","doi-asserted-by":"publisher","unstructured":"Singh, A., Brooks, C. A., & Doroudi, S. (2022). Learnersourcing in Theory and Practice: Synthesizing the Literature and Charting the Future. Proceedings of the Ninth ACM Conference on Learning @ Scale. https:\/\/doi.org\/10.1145\/3491140.3528277.","DOI":"10.1145\/3491140.3528277"},{"issue":"7","key":"12851_CR67","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1002\/asi.24297","volume":"71","author":"W Tay","year":"2020","unstructured":"Tay, W., Zhang, X., & Karimi, S. (2020). Beyond mean rating: Probabilistic aggregation of star ratings based on helpfulness. Journal of the Association for Information Science and Technology, 71(7), 784\u2013799. https:\/\/doi.org\/10.1002\/asi.24297","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"12851_CR68","doi-asserted-by":"crossref","unstructured":"Tyen, G., Mansoor, H., Chen, P., Mak, T., & C\u0103rbune, V. (2023). LLMs cannot find reasoning errors, but can correct them!. arXiv preprint arXiv:2311.08516.","DOI":"10.18653\/v1\/2024.findings-acl.826"},{"issue":"2","key":"12851_CR69","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1080\/07421222.2019.1598692","volume":"36","author":"S Velichety","year":"2019","unstructured":"Velichety, S., Ram, S., & Bockstedt, J. (2019). Quality Assessment of Peer-Produced Content in Knowledge Repositories using Development and Coordination Activities. Journal of Management Information Systems, 36(2), 478\u2013512. https:\/\/doi.org\/10.1080\/07421222.2019.1598692","journal-title":"Journal of Management Information Systems"},{"issue":"1","key":"12851_CR70","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TSC.2010.56","volume":"5","author":"X Wang","year":"2012","unstructured":"Wang, X., Liu, L., & Su, J. (2012). RLM: A General Model for Trust Representation and Aggregation. IEEE Transactions on Services Computing, 5(1), 131\u2013143. https:\/\/doi.org\/10.1109\/TSC.2010.56","journal-title":"IEEE Transactions on Services Computing"},{"key":"12851_CR71","doi-asserted-by":"publisher","first-page":"115089","DOI":"10.1016\/j.eswa.2021.115089","volume":"181","author":"P Wang","year":"2021","unstructured":"Wang, P., Li, M., Li, X., Zhou, H., & Hou, J. (2021). A hybrid approach to classifying Wikipedia article quality flaws with feature fusion framework. Expert Systems with Applications, 181, 115089. https:\/\/doi.org\/10.1016\/j.eswa.2021.115089","journal-title":"Expert Systems with Applications"},{"key":"12851_CR72","unstructured":"Wang, J., Sun, Q., Chen, N., Li, X., & Gao, M. (2023). Boosting Language Models Reasoning with Chain-of-Knowledge Prompting. arXiv preprint arXiv:2306.06427."},{"key":"12851_CR73","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, X., & Chen, W. (2023). Augmenting black-box llms with medical textbooks for clinical question answering. arXiv preprint arXiv:2309.02233.","DOI":"10.18653\/v1\/2024.findings-emnlp.95"},{"key":"12851_CR74","doi-asserted-by":"publisher","unstructured":"Warncke-Wang, M., Cosley, D., & Riedl, J. (2013). Tell me more: an actionable quality model for Wikipedia. In Proceedings of the 9th International Symposium on Open Collaboration (pp. 1\u201310). https:\/\/doi.org\/10.1145\/2491055.2491063.","DOI":"10.1145\/2491055.2491063"},{"key":"12851_CR75","unstructured":"Wei, X., Wang, S., Zhang, D., Bhatia, P., & Arnold, A. (2021). Knowledge enhanced pretrained language models: A compreshensive survey. arXiv preprint arXiv:2110.08455."},{"key":"12851_CR76","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"12851_CR77","volume-title":"Do Learners Know What\u2019s Good for Them?","author":"J Whitehill","year":"2019","unstructured":"Whitehill, J., Aguerrebere, C., & Hylak, B. (2019). Do Learners Know What\u2019s Good for Them? International Educational Data Mining Society."},{"key":"12851_CR78","doi-asserted-by":"publisher","unstructured":"Wu, X., He, X., Liu, T., Liu, N., & Zhai, X. (2023). Matching Exemplar as\u00a0Next Sentence Prediction (MeNSP): Zero-Shot Prompt Learning for\u00a0Automatic Scoring in\u00a0Science Education. In N. Wang, G. Rebolledo-Mendez, N. Matsuda, O. C. Santos, & V. Dimitrova (Eds.), Artificial Intelligence in Education (pp. 401\u2013413). https:\/\/doi.org\/10.1007\/978-3-031-36272-9_33.","DOI":"10.1007\/978-3-031-36272-9_33"},{"key":"12851_CR79","unstructured":"Xiong, M., Hu, Z., Lu, X., Li, Y., Fu, J., He, J., & Hooi, B. (2023). Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. arXiv preprint arXiv:2306.13063."},{"key":"12851_CR80","doi-asserted-by":"publisher","first-page":"50466","DOI":"10.1109\/ACCESS.2021.3069055","volume":"9","author":"J Xu","year":"2021","unstructured":"Xu, J., Li, Q., Liu, J., Lv, P., & Yu, G. (2021). Leveraging Cognitive Diagnosis to Improve Peer Assessment in MOOCs. IEEE Access, 9, 50466\u201350484. https:\/\/doi.org\/10.1109\/ACCESS.2021.3069055","journal-title":"IEEE Access"},{"key":"12851_CR81","unstructured":"Xu, B., Yang, A., Lin, J., Wang, Q., Zhou, C., Zhang, Y., & Mao, Z. (2023). ExpertPrompting: Instructing Large Language Models to be Distinguished Experts. arXiv preprint arXiv:2305.14688."},{"issue":"1","key":"12851_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/jcal.12111","volume":"32","author":"X Yang","year":"2016","unstructured":"Yang, X., Guo, X., & Yu, S. (2016). Student-generated content in college teaching: Content quality, behavioural pattern and learning performance: Student-generated content in college teaching. Journal of Computer Assisted Learning, 32(1), 1\u201315. https:\/\/doi.org\/10.1111\/jcal.12111","journal-title":"Journal of Computer Assisted Learning"},{"key":"12851_CR83","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022). React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629."},{"key":"12851_CR84","doi-asserted-by":"publisher","unstructured":"Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023). Tree of Thoughts: Deliberate Problem Solving with Large Language Models. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2305.10601.","DOI":"10.48550\/arXiv.2305.10601"},{"key":"12851_CR85","unstructured":"Yao, J. Y., Ning, K. P., Liu, Z. H., Ning, M. N., & Yuan, L. (2023). Llm lies: Hallucinations are not bugs, but features as adversarial examples. arXiv preprint arXiv:2310.01469."}],"container-title":["Education and Information Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10639-024-12851-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10639-024-12851-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10639-024-12851-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:41:27Z","timestamp":1738820487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10639-024-12851-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":85,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["12851"],"URL":"https:\/\/doi.org\/10.1007\/s10639-024-12851-4","relation":{},"ISSN":["1360-2357","1573-7608"],"issn-type":[{"value":"1360-2357","type":"print"},{"value":"1573-7608","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"4 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The study sought and got ethical approval from the Research Ethical Board of the author\u2019s institution. Authors took all necessary measures to anonymize personally identifiable information, ensuring that the identities of participants are not disclosed. Authors provided all participants with clear and easily understandable information. Authors ensured that they fully understood how and why their created content would be collected. Authors confirmed that they were aware their participation was voluntary and that they could withdraw their consent at any time without any negative consequences.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}