{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T19:31:07Z","timestamp":1772652667927,"version":"3.50.1"},"reference-count":147,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"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\/s40593-025-00487-5","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T16:19:10Z","timestamp":1750090750000},"page":"2923-2974","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Conceptual Hybrid Framework for the Automated Assessment of Short Answers"],"prefix":"10.1016","volume":"35","author":[{"given":"Vidasha","family":"Ramnarain-Seetohul","sequence":"first","affiliation":[]},{"given":"Yasmine","family":"Rosunally","sequence":"additional","affiliation":[]},{"given":"Vandana","family":"Bassoo","sequence":"additional","affiliation":[]}],"member":"78","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"487_CR1","doi-asserted-by":"publisher","first-page":"76433","DOI":"10.1109\/ACCESS.2021.3082408","volume":"9","author":"HA Abdelaber","year":"2021","unstructured":"Abdelaber, H. A. (2021). Automatic arabic short answers scoring using longest common subsequence and arabic wordnet. IEEE Access, 9, 76433\u201376445. https:\/\/doi.org\/10.1109\/ACCESS.2021.3082408","journal-title":"IEEE Access"},{"issue":"8","key":"487_CR2","doi-asserted-by":"publisher","first-page":"e0272269","DOI":"10.1371\/journal.pone.0272269","volume":"17","author":"M Abdul Salam","year":"2022","unstructured":"Abdul Salam, M., El-Fatah, M. A., & Hassan, N. F. (2022). Automatic grading for Arabic short answer questions using optimized deep learning model. Plos one, 17(8), e0272269. https:\/\/doi.org\/10.1371\/journal.pone.0272269","journal-title":"Plos one"},{"key":"487_CR3","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Jain, A., & Reed, B. (2022). CodEval: Improving Student success in programming assignments. Preprint retrieved from https:\/\/arxiv.org\/abs\/2211.11883","DOI":"10.21125\/edulearn.2022.1767"},{"key":"487_CR4","doi-asserted-by":"publisher","unstructured":"Ahmed, A., Joorabchi, A., & Hayes, M. J. (2022). On deep learning approaches to automated assessment: Strategies for short answer grading. In Proceedings of the 14th international conference on computer supported education (CSEDU 2022) (Vol. 2, pp. 85\u201394). https:\/\/doi.org\/10.5220\/0011082100003182","DOI":"10.5220\/0011082100003182"},{"key":"487_CR5","doi-asserted-by":"crossref","unstructured":"Alonso, J. M., Castiello, M. C., Magdalena, L., spsampsps Mencar, C. (2021). Toward explainable artificial intelligence through fuzzy system. In J. Kacprzyk (Ed.), Explainable fuzzy systems paving the way from interpretable fuzzy systems to explainable AI systems (vol. 970 Series). Polish Academy of Sciences, Springer.","DOI":"10.1007\/978-3-030-71098-9_1"},{"key":"487_CR6","unstructured":"Alvarado Mantecon, G. (2019). Towards the automatic classification of student answers to open-ended questions Master\u2019s thesis, University of Ottawa. uO Research. https:\/\/ruor.uottawa.ca\/handle\/10393\/39093. Accessed 10 Nov 2024."},{"issue":"1","key":"487_CR7","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s13173-015-0039-7","volume":"21","author":"JC Alves dos Santos","year":"2015","unstructured":"Alves dos Santos, J. C., & Favero, E. L. (2015). Practical use of a latent semantic analysis (LSA) model for automatic evaluation of written answers. Journal of the Brazilian Computer Society, 21(1), 21. https:\/\/doi.org\/10.1186\/s13173-015-0039-7","journal-title":"Journal of the Brazilian Computer Society"},{"key":"487_CR8","doi-asserted-by":"publisher","unstructured":"Arrieta, A. B., D\u00edaz-Rodr\u00edguez, N., Ser, J. D., Bennetot, A., Tabik, S., Barbado, A., . . . Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82\u2013115. https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"487_CR9","doi-asserted-by":"publisher","unstructured":"Baral, S., Botelho, A., Santhanam, A., Gurung, A., Cheng, L., & Heffernan, N. (2023). Auto-scoring student responses with images in mathematics. In T. K. M. Feng (Ed.), Proceedings of the 16th international conference on educational data mining (pp. 362\u2013369). International Educational Data Mining Society. https:\/\/doi.org\/10.5281\/zenodo.8115645","DOI":"10.5281\/zenodo.8115645"},{"key":"487_CR10","doi-asserted-by":"publisher","DOI":"10.3991\/ijet.v5i2.1235","author":"T Barker","year":"2010","unstructured":"Barker, T. (2010). An Automated feedback system based on adaptive testing: Extending the model. International Journal of Emerging Technologies in Learning (iJET). https:\/\/doi.org\/10.3991\/ijet.v5i2.1235","journal-title":"International Journal of Emerging Technologies in Learning (iJET)"},{"key":"487_CR11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804489","volume-title":"Corpus linguistics: Investigating language structure and use","author":"D Biber","year":"1998","unstructured":"Biber, D., Conrad, S., & Reppen, R. (1998). Corpus linguistics: Investigating language structure and use. Cambridge University Press. https:\/\/doi.org\/10.1017\/CBO9780511804489"},{"key":"487_CR12","volume-title":"A Comparative study of data splitting algorithms for machine learning model selection, electrical engineering and computer science","author":"DE Birba","year":"2020","unstructured":"Birba, D. E. (2020). A Comparative study of data splitting algorithms for machine learning model selection, electrical engineering and computer science. Kth Royal Institute Of Technology."},{"key":"487_CR13","doi-asserted-by":"publisher","first-page":"117315","DOI":"10.1016\/j.eswa.2022.117315","volume":"203","author":"N Birla","year":"2022","unstructured":"Birla, N., Jain, M. K., & Panwar, A. (2022). Automated assessment of subjective assignments: A hybrid approach. Expert Systems with Applications, 203, 117315.","journal-title":"Expert Systems with Applications"},{"key":"487_CR14","doi-asserted-by":"publisher","first-page":"106292","DOI":"10.1016\/j.engappai.2023.106292","volume":"123","author":"S Bonthu","year":"2023","unstructured":"Bonthu, S., Sree, S. R., & Prasad, M. K. (2023). Improving the performance of automatic short answer grading using transfer learning and augmentation. Engineering Applications of Artificial Intelligence, 123, 106292. https:\/\/doi.org\/10.1016\/j.engappai.2023.106292","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"487_CR15","doi-asserted-by":"publisher","unstructured":"Bonthu, S., Rama Sree, S., spsampsps Krishna Prasad, M. H. M. (2021). Automated short answer grading using deep learning: A survey. In machine learning and knowledge extraction: 5th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 international cross-domain conference, CD-MAKE 2021, virtual event, August 17\u201320, 2021, proceedings 5\u00a0(pp. 61-78). Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-030-84060-0_5","DOI":"10.1007\/978-3-030-84060-0_5"},{"key":"487_CR16","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s40593-014-0026-8","volume":"25","author":"S Burrows","year":"2015","unstructured":"Burrows, S., Gurevych, I., & Stein, B. (2015). The eras and trends of automatic short answer grading. International Journal of Artificial Intelligence in Education, 25, 60\u2013117. https:\/\/doi.org\/10.1007\/s40593-014-0026-8","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"487_CR17","unstructured":"Burstein, J., Kaplan, R., Wolff, S., & Lu, C. (1996). Using lexical semantic techniques to classify free-responses. In E. Viegas (Ed.), Proceedings of the ACL SIGLEX workshop on breadth and depth of semantic lexicons (pp. 20\u201329). Association for Computational Linguistics."},{"key":"487_CR18","unstructured":"Buslaev, A., Parinov, A., Khvedchenya, E., Iglovikov, V. I., & Kalinin, A. A. (2018). Albumentations: fast and flexible image augmentations. Preprint retrieved from https:\/\/arxiv.org\/abs\/1809.06839"},{"key":"487_CR19","doi-asserted-by":"publisher","unstructured":"Camus, L., spsampsps Filighera, A. (2020). Investigating transformers for automatic short answer grading. In artificial intelligence in education: 21st international conference, AIED 2020, Ifrane, Morocco, July 6\u201310, 2020, proceedings, Part II 21\u00a0(pp. 43-48). Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-030-52240-7_8","DOI":"10.1007\/978-3-030-52240-7_8"},{"key":"487_CR20","unstructured":"Carter, K. P. (2019). Investigating student conceptual understanding of structure and function by using formative assessment and automated scoring models (Doctoral dissertation, University of South Florida). University of South Florida Scholar Commons. Retrieved January 15, 2024, from https:\/\/digitalcommons.usf.edu\/etd\/7761"},{"issue":"3\/4","key":"487_CR21","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1504\/IJAIP.2019.103413","volume":"14","author":"UK Chakraborty","year":"2019","unstructured":"Chakraborty, U. K., Konar, D., Roy, S., & Choudhury, S. (2019). Automatic short answer grading using rough concept clusters. International Journal of Advanced Intelligence Paradigms (IJAIP), 14(3\/4), 260\u2013280. https:\/\/doi.org\/10.1504\/IJAIP.2019.103413","journal-title":"International Journal of Advanced Intelligence Paradigms (IJAIP)"},{"key":"487_CR22","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1162\/tacl_a_00542","volume":"11","author":"J Chen","year":"2023","unstructured":"Chen, J., Tam, D., Raffel, C., Bansal, M., & Yang, D. (2023a). An empirical survey of data augmentation for limited data learning in NLP. Transactions of the Association for Computational Linguistics, 11, 191\u2013211. https:\/\/doi.org\/10.1162\/tacl_a_00542","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"487_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3260840","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Luo, J., Zhu, X., Wu, H., & Yuan, S. (2023b). A cross-lingual hybrid neural network with interaction enhancement for grading short-answer texts. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3260840","journal-title":"IEEE Access"},{"key":"487_CR24","doi-asserted-by":"crossref","unstructured":"Chevrie, F., & Guely, F. (1998). Cahier technique No. 191: Fuzzy logic. Schneider Electric. https:\/\/www.studiecd.dk\/cahiers_techniques\/Fuzzy_logic.pdf","DOI":"10.1007\/978-1-4615-4068-7_3"},{"key":"487_CR25","unstructured":"Chimatapu, R. (2021). An explainable artificial intelligence approach based on deep type-2 fuzzy logic system (Doctoral dissertation, University of Essex). University of Essex Repository. Retrieved January 20, 2024, from https:\/\/repository.essex.ac.uk\/30770\/"},{"issue":"1","key":"487_CR26","doi-asserted-by":"publisher","first-page":"37","DOI":"10.18608\/jla.2023.7801","volume":"10","author":"R Conijn","year":"2023","unstructured":"Conijn, R., Kahr, P., & Snijders, C. C. (2023). The effects of explanations in automated essay scoring systems on student trust and motivation. Journal of Learning Analytics, 10(1), 37\u201353. https:\/\/doi.org\/10.18608\/jla.2023.7801","journal-title":"Journal of Learning Analytics"},{"key":"487_CR27","first-page":"241","volume-title":"Handbook of natural language processing","author":"J Cowie","year":"2000","unstructured":"Cowie, J., & Wilks, Y. (2000). Information extraction. In R. Dale, H. Moisl, & H. Somers (Eds.), Handbook of natural language processing (1st ed., pp. 241\u2013260). Marcel Dekker.","edition":"1"},{"key":"487_CR28","doi-asserted-by":"crossref","unstructured":"Daramola, O., Afolabi, I., Akinyemi, I., & Oladipupo, O. (2013). Using ontology-based information extraction for subject-based auto-grading. In international conference on knowledge engineering and ontology development\u00a0(Vol. 2, pp. 373-378). SCITEPRESS.","DOI":"10.5220\/0004625903730378"},{"key":"487_CR29","doi-asserted-by":"publisher","unstructured":"Darvishzadeh, A., Entezari, N., & Stahovich, T. (2018). Finding the answer: Techniques for locating students' answers in handwritten problem solutions. In\u00a02018 16th international conference on frontiers in handwriting recognition (ICFHR)\u00a0(pp. 587-592). IEEE, Niagara Falls, NY, USA, 05-08 August 2018. https:\/\/doi.org\/10.1109\/ICFHR-2018.2018.00108","DOI":"10.1109\/ICFHR-2018.2018.00108"},{"issue":"4","key":"487_CR30","doi-asserted-by":"publisher","first-page":"374","DOI":"10.14742\/ajet.1198","volume":"24","author":"JC Debuse","year":"2008","unstructured":"Debuse, J. C., Lawley, M., & Shibl, R. (2008). Educators\u2019 perceptions of automated feedback systems. Australasian Journal of Educational Technology, 24(4), 374\u2013386.","journal-title":"Australasian Journal of Educational Technology"},{"key":"487_CR31","doi-asserted-by":"publisher","first-page":"101258","DOI":"10.1016\/j.stueduc.2023.101258","volume":"77","author":"E Del Gobbo","year":"2023","unstructured":"Del Gobbo, E., Guarino, A., Cafarelli, B., Grilli, L., & Limone, P. (2023). Automatic evaluation of open-ended questions for online learning. A systematic mapping. Studies in Educational Evaluation, 77, 101258. https:\/\/doi.org\/10.1016\/j.stueduc.2023.101258","journal-title":"Studies in Educational Evaluation"},{"key":"487_CR32","doi-asserted-by":"publisher","DOI":"10.1051\/itmconf\/20214003032","author":"S Dhabekar","year":"2021","unstructured":"Dhabekar, S., & Patil, D. M. (2021). Implementation of deep learning based sentiment classification and product aspect analysis. ITM Web of Conferences. https:\/\/doi.org\/10.1051\/itmconf\/20214003032","journal-title":"ITM Web of Conferences"},{"key":"487_CR33","unstructured":"Doewes, A., Kurdhi, N. A., & Saxena, A. (2023). Evaluating quadratic weighted kappa as the standard performance metric for automated essay scoring. In M. Feng, T. Kaser, & P. Talukdar (Ed.), Proceedings of the 16th international conference on educational data mining (pp. 103\u2013113). International Educational Data Mining Society."},{"issue":"2","key":"487_CR34","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1080\/08957347.2014.1002920","volume":"28","author":"E Donald","year":"2015","unstructured":"Donald, E., Escoffery, D. S., & Duchnowski, M. P. (2015). Validating automated essay scoring: A (Modest) refinement of the \u201cGold Standard\u201d powers. Applied Measurement in Education, 28(2), 130\u2013142.","journal-title":"Applied Measurement in Education"},{"issue":"4","key":"487_CR35","doi-asserted-by":"publisher","first-page":"266","DOI":"10.3390\/educsci12040266","volume":"12","author":"D Doz","year":"2022","unstructured":"Doz, D., Felda, D., & Coti\u010d, M. (2022). Assessing students\u2019 mathematical knowledge with fuzzy logic. Education Sciences, 12(4), 266. https:\/\/doi.org\/10.3390\/educsci12040266","journal-title":"Education Sciences"},{"key":"487_CR36","doi-asserted-by":"publisher","unstructured":"Elnakaa, A., Naela, O., Afifia, H., & Sharaf, N. (2021). AraScore: Investigating response-based Arabic short answer scoring. Procedia Computer Science, 189, 282\u2013291. https:\/\/doi.org\/10.1016\/j.procs.2021.05.091","DOI":"10.1016\/j.procs.2021.05.091"},{"key":"487_CR37","unstructured":"Faiz, A., Kaneda, S., Wang, R., Osi, R. C., Sharma, P., Chen, F., & Jiang, L. (2024). LLMCarbon: Modeling the end-to-end carbon footprint of large language models. In The twelfth international conference on learning representations (ICLR 2024). https:\/\/openreview.net\/forum?id=aIok3ZD9to"},{"key":"487_CR38","doi-asserted-by":"publisher","first-page":"652801","DOI":"10.3389\/fenrg.2021.652801","volume":"9","author":"C Fan","year":"2021","unstructured":"Fan, C., Chen, M., Wang, X., Wang, J., & Huang, B. (2021). A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data. Frontiers in Energy Research, 9, 652801. https:\/\/doi.org\/10.3389\/fenrg.2021.652801","journal-title":"Frontiers in Energy Research"},{"key":"487_CR39","doi-asserted-by":"publisher","unstructured":"Farouk, M. (2019). Measuring sentences similarity: A survey. Indian Journal of Science and Technology, 12(25). https:\/\/doi.org\/10.17485\/ijst\/2019\/v12i25\/143977","DOI":"10.17485\/ijst\/2019\/v12i25\/143977"},{"key":"487_CR40","doi-asserted-by":"publisher","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. In Findings of the association for computational linguistics: ACL-IJCNLP 2021 (pp. 968\u2013988). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.84","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"487_CR41","doi-asserted-by":"publisher","unstructured":"Ferreira Mello, R., Pereira J\u00fanior, C., Rodrigues, L., Pereira, F. D., Cabral, L., Costa, N., Ramalho, G., & Ga\u0161evi\u0107, D. (2025). Automatic short answer grading in the LLM era: Does GPT-4 with prompt engineering beat traditional models? In Proceedings of the 15th international learning analytics and knowledge conference (pp. 93\u2013103). Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3706468.3706481","DOI":"10.1145\/3706468.3706481"},{"key":"487_CR42","unstructured":"Frick, R. A., & Vogel, I. (2022). Fraunhofer SIT at CheckThat! 2022: Ensemble similarity estimation for finding previously fact-checked claims. In CLEF 2022: Conference and labs of the evaluation forum."},{"key":"487_CR43","doi-asserted-by":"publisher","unstructured":"Galhardi, L., spsampsps Brancher, J. (2018). Machine learning approach for automatic short answer grading: A systematic review. 16th Ibero-American conference on artificial intelligence (pp. 380\u2013391). Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-03928-8_31","DOI":"10.1007\/978-3-030-03928-8_31"},{"key":"487_CR44","doi-asserted-by":"crossref","unstructured":"Garc\u00eda, S., Luengo, J., spsampsps Herrera, F. (2015). Data Preprocessing in Data Mining. In J. Kacprzyk, spsampsps L. C. Jain (Eds.), Intelligent systems reference library 72. Springer International Publishing.","DOI":"10.1007\/978-3-319-10247-4"},{"key":"487_CR45","doi-asserted-by":"publisher","unstructured":"Gautam, D., & Rus, V. (2020). Using neural tensor networks for open ended short answer assessment. In I. Bittencourt, M. Cukurova, K. Muldner, R. Luckin, & E. Mill\u00e1n (Eds.), Artificial intelligence in education: AIED 2020 (pp. 191\u2013203). Springer. https:\/\/doi.org\/10.1007\/978-3-030-52237-7_16","DOI":"10.1007\/978-3-030-52237-7_16"},{"key":"487_CR46","doi-asserted-by":"publisher","unstructured":"Ghavidel, H., Zouaq, A., & Desmarais, M. (2020). Using BERT and XLNET for the automatic short answer grading task. In Proceedings of the 12th international conference on computer supported education (CSEDU 2020) (Vol. 1, pp. 58\u201367). https:\/\/doi.org\/10.5220\/0009422400580067","DOI":"10.5220\/0009422400580067"},{"key":"487_CR47","doi-asserted-by":"publisher","unstructured":"Ghelani, D. (2022). A review on student automatic grading system Master's thesis, Gujarat Technological University. Authorea. https:\/\/doi.org\/10.22541\/au.166455370.07823799\/v1","DOI":"10.22541\/au.166455370.07823799\/v1"},{"key":"487_CR48","doi-asserted-by":"publisher","unstructured":"Ghosh, S., & Chopra, A. (2021). Using transformer based ensemble learning to classify scientific articles. In Trends and applications in knowledge discovery and data mining (pp. 159\u2013170). Springer. https:\/\/doi.org\/10.48550\/arXiv.2102.09991","DOI":"10.48550\/arXiv.2102.09991"},{"key":"487_CR49","doi-asserted-by":"publisher","unstructured":"Ghosh, S., & Fatima, S. S. (2010). Design of an automated essay grading (AEG) system in Indian context. International Journal of Computer Applications, 1(11), 237\u2013391. https:\/\/doi.org\/10.5120\/237-391","DOI":"10.5120\/237-391"},{"issue":"2","key":"487_CR50","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1207\/s15326950dp3802_2","volume":"38","author":"A Graesser","year":"2004","unstructured":"Graesser, A., McNamara, D., & Kulikowich, J. (2004). Coh-Metrix: Analysis of texts and textual cues that foster comprehension. Discourse Processes, 38(2), 109\u2013141. https:\/\/doi.org\/10.1207\/s15326950dp3802_2","journal-title":"Discourse Processes"},{"key":"487_CR51","doi-asserted-by":"publisher","unstructured":"Guarino, N., Oberle, D., & Staab, S. (2009). What is an ontology? In S. Staab & R. Studer (Eds.), Handbook on ontologies (2nd ed., pp. 1\u201317). Springer. https:\/\/doi.org\/10.1007\/978-3-540-92673-3_0","DOI":"10.1007\/978-3-540-92673-3_0"},{"key":"487_CR52","doi-asserted-by":"crossref","unstructured":"Gupta, K. (2023). Data augmentation for automated essay scoring using transformer models. Preprint retrieved from https:\/\/arxiv.org\/abs\/2210.12809","DOI":"10.1109\/AISC56616.2023.10085523"},{"issue":"6","key":"487_CR53","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1177\/0165551515610989","volume":"42","author":"F Gutierrez","year":"2016","unstructured":"Gutierrez, F., Dou, D., Fickas, S., Wimalasuriya, D., & Zong, H. (2016). A hybrid ontology-based information extraction system. Journal of Information Science, 42(6), 798\u2013820.","journal-title":"Journal of Information Science"},{"key":"487_CR54","doi-asserted-by":"publisher","unstructured":"Gutierrez, F., Dou, D., Martini, A., Fickas, S., & Zong, H. (2013). Hybrid ontology-based information extraction for automated text grading. In\u00a02013 12th international conference on machine learning and applications\u00a0(Vol. 1, pp. 359-364). IEEE, Miami, FL, USA, 04-07 December 2013.\u00a0https:\/\/doi.org\/10.1109\/ICMLA.2013.73","DOI":"10.1109\/ICMLA.2013.73"},{"key":"487_CR55","unstructured":"Haller, S., Aldea, A., Seifert, C., & Strisciuglio, N. (2022). Survey on automated short answer grading with deep learning: From word embeddings to transformers. Preprint retrieved from https:\/\/arxiv.org\/abs\/2204.03503"},{"issue":"3","key":"487_CR56","doi-asserted-by":"publisher","first-page":"622","DOI":"10.3758\/s13428-012-0214-0","volume":"44","author":"P Hastings","year":"2012","unstructured":"Hastings, P., Hughes, S., Magliano, J. P., Goldman, S. R., & Lawless, K. (2012). Assessing the use of multiple sources in student essays. Behavior Research Methods, 44(3), 622\u2013633.","journal-title":"Behavior Research Methods"},{"key":"487_CR57","unstructured":"Higgins, D., Brew, C., Heilman, M., Ziai, R., Chen, L., Cahill, A., . . . Blackmore, J. (2014). Is getting the right answer just about choosing the right words? The role of syntactically-informed features in short answer scoring. Preprint retrieved from. https:\/\/arxiv.org\/abs\/1403.0801"},{"issue":"3\u20134","key":"487_CR58","doi-asserted-by":"publisher","first-page":"46","DOI":"10.2991\/nlpr.d.210212.001","volume":"1","author":"EY Ince","year":"2021","unstructured":"Ince, E. Y., & Kutlu, A. (2021). Web-based Turkish automatic short-answer grading system. Natural Language Processing Research, 1(3\u20134), 46\u201355. https:\/\/doi.org\/10.2991\/nlpr.d.210212.001","journal-title":"Natural Language Processing Research"},{"key":"487_CR59","doi-asserted-by":"publisher","unstructured":"Ivanova, V., & Zlatanov, B. (2019). Application of fuzzy logic in online test evaluation in English as a foreign language at university level. In Proceedings of the 45th international conference on application of mathematics in engineering and economics (AMEE'19) (AIP Conference Proceedings Vol. 2172). AIP Publishing. https:\/\/doi.org\/10.1063\/1.5133519","DOI":"10.1063\/1.5133519"},{"issue":"1","key":"487_CR60","doi-asserted-by":"publisher","first-page":"6906587","DOI":"10.1155\/2022\/6906587","volume":"2022","author":"YJ Jong","year":"2022","unstructured":"Jong, Y. J., Kim, Y. J., & Ri, O. C. (2022). Improving performance of automated essay scoring by using back-translation essays and adjusted scores. Mathematical Problems in Engineering, 2022(1), 6906587. https:\/\/doi.org\/10.1155\/2022\/6906587","journal-title":"Mathematical Problems in Engineering"},{"issue":"4","key":"487_CR61","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1002\/sam.11583","volume":"15","author":"VR Joseph","year":"2022","unstructured":"Joseph, V. R. (2022). Optimal ratio for data splitting. Statistical Analysis and Data Mining: The ASA Data Science Journal, 15(4), 531\u2013538. https:\/\/doi.org\/10.1002\/sam.11583","journal-title":"Statistical Analysis and Data Mining: The ASA Data Science Journal"},{"key":"487_CR62","unstructured":"Kaggle. (2012). The hewlett foundation: Automated essay scoring. Retrieved December 20, 2023, from https:\/\/www.kaggle.com\/c\/asap-aes\/overview\/evaluation"},{"key":"487_CR63","doi-asserted-by":"publisher","first-page":"158","DOI":"10.30495\/tfss.2023.1976303.1060","volume":"2","author":"C Kahraman","year":"2023","unstructured":"Kahraman, C., Onar, S. C., Oztaysi, B., & Cebi, S. (2023). Role of fuzzy sets on artificial intelligence methods: A literature review. Transactions on Fuzzy Sets and Systems (TFSS), 2, 158\u2013178. https:\/\/doi.org\/10.30495\/tfss.2023.1976303.1060","journal-title":"Transactions on Fuzzy Sets and Systems (TFSS)"},{"key":"487_CR64","doi-asserted-by":"publisher","unstructured":"Kamr, A. M., & Mohamed, E. (2022). akaBERT at SemEval-2022 Task 6: An ensemble transformer-based model for Arabic sarcasm detection. In Proceedings of the 16th international workshop on semantic evaluation (SemEval-2022) (pp. 885\u2013890). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.semeval-1.124","DOI":"10.18653\/v1\/2022.semeval-1.124"},{"key":"487_CR65","doi-asserted-by":"publisher","first-page":"3353","DOI":"10.1007\/s00500-015-1916-x","volume":"19","author":"P Kazienko","year":"2015","unstructured":"Kazienko, P., Lughofer, E., & Trawinski, B. (2015). Editorial on the special issue \u201cHybrid and ensemble techniques in soft computing: Recent advances and emerging trends.\u201d Soft Computing, 19, 3353\u20133355. https:\/\/doi.org\/10.1007\/s00500-015-1916-x","journal-title":"Soft Computing"},{"key":"487_CR66","doi-asserted-by":"publisher","unstructured":"Ko, T., Peddinti, V., Povey, D., & Khudanpur, S. (2015). Audio augmentation for speech recognition. In Proceedings of the annual conference of the international speech communication association (INTERSPEECH 2015) (pp. 3586\u20133589). https:\/\/doi.org\/10.21437\/Interspeech.2015-711","DOI":"10.21437\/Interspeech.2015-711"},{"key":"487_CR67","doi-asserted-by":"publisher","unstructured":"Kortemeyer, G. (2024). Performance of the pre trained large language model GPT 4 on automated short answer grading. Discover Artificial Intelligence, 4,. https:\/\/doi.org\/10.1007\/s44163-024-00147-y","DOI":"10.1007\/s44163-024-00147-y"},{"key":"487_CR68","doi-asserted-by":"publisher","unstructured":"Kowsari, K., Jafari Meimandi, K., Heidarysafa, M., Mendu, S., Barnes, L., & Brown, D. (2019). Text classification algorithms: A survey. Information, 10(1). https:\/\/doi.org\/10.3390\/info10010001","DOI":"10.3390\/info10010001"},{"key":"487_CR69","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In F. Pereira, C. J. C. Burges, L. Bottou, & K. Q. Weinberger (Eds.), Advances in neural information processing systems (Vol. 25, pp. 1097\u20131105). https:\/\/papers.nips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"487_CR70","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/s40593-020-00211-5","volume":"31","author":"V Kumar","year":"2021","unstructured":"Kumar, V., & Boulanger, D. (2021). Automated essay scoring and the deep learning black box: How are rubric scores determined? International Journal of Artificial Intelligence in Education, 31, 538\u2013584. https:\/\/doi.org\/10.1007\/s40593-020-00211-5","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"487_CR71","doi-asserted-by":"publisher","unstructured":"Kumar, A., Sharma, A., & Nayyar, A. (2020). Fuzzy logic based hybrid model for automatic extractive text summarization. In Proceedings of the 2020 5th international conference on intelligent information technology (ICIIT 2020). ACM. https:\/\/doi.org\/10.1145\/3385209.3385235","DOI":"10.1145\/3385209.3385235"},{"key":"487_CR72","doi-asserted-by":"publisher","unstructured":"Landauer, T. K., Laham, D., & Foltz, P. (2003). Automatic essay assessment. Assessment in Education Principles Policy and Practice, 10(3). https:\/\/doi.org\/10.1080\/0969594032000148154","DOI":"10.1080\/0969594032000148154"},{"issue":"2","key":"487_CR73","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1177\/0013164419860575","volume":"80","author":"N LaVoie","year":"2019","unstructured":"LaVoie, N., Parker, J., Legree, P. J., Ardison, S., & Kilcullen, R. N. (2019). Using latent semantic analysis to score short answer constructed responses: Automated scoring of the consequences test. Educational and Psychological Measurement, 80(2), 399\u2013414. https:\/\/doi.org\/10.1177\/0013164419860575","journal-title":"Educational and Psychological Measurement"},{"key":"487_CR74","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/A:1025779619903","volume":"37","author":"C Leacock","year":"2003","unstructured":"Leacock, C., & Chodorow, M. (2003). C-rater: Automatic scoring of short answer questions. Computers and the Humanities, 37, 389\u2013405. https:\/\/doi.org\/10.1023\/A:1025779619903","journal-title":"Computers and the Humanities"},{"key":"487_CR75","doi-asserted-by":"publisher","unstructured":"LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 436\u2013444,. https:\/\/doi.org\/10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"487_CR76","doi-asserted-by":"publisher","unstructured":"Lezmi, E., & Xu, J. (2023). Time series forecasting with transformer models and application to asset management. SSRN. https:\/\/doi.org\/10.2139\/ssrn.4375798","DOI":"10.2139\/ssrn.4375798"},{"key":"487_CR77","unstructured":"Li, X., Yue, T., Huang, X., Yang, Z., & Gang, X. (2019). BAGS: An automatic homework grading system using the pictures taken by smart phones. Preprint retrieved https:\/\/arxiv.org\/abs\/1906.03767"},{"key":"487_CR78","doi-asserted-by":"publisher","unstructured":"Liew, P. Y., & Tan., I. K. (2024). On automated essay grading using large language models. 8th international conference on computer science and artificial intelligence (CSAI) (CSAI 2024). Beijing, China: ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/3709026.3709030","DOI":"10.1145\/3709026.3709030"},{"issue":"3","key":"487_CR79","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.47836\/pjst.29.3.27","volume":"29","author":"CT Lim","year":"2021","unstructured":"Lim, C. T., Bong, C. H., Wong, W. S., & Lee, N. K. (2021). A comprehensive review of automated essay scoring (AES) research and development. Pertanika Journal of Science and Technology, 29(3), 1875\u20131899.","journal-title":"Pertanika Journal of Science and Technology"},{"key":"487_CR80","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baac056","author":"S-J Lin","year":"2022","unstructured":"Lin, S.-J., Yeh, W.-C., Chiu, Y.-W., Chang, Y.-C., Hsu, M.-H., Chen, Y.-S., & Hsu, W.-L. (2022). A BERT-based ensemble learning approach for the BioCreative VII challenges: Full-text chemical identification and multi-label classification in PubMed articles. Database (Oxford). https:\/\/doi.org\/10.1093\/database\/baac056","journal-title":"Database (Oxford)"},{"key":"487_CR81","doi-asserted-by":"publisher","unstructured":"Liu, S., Liu, S., Sha, L., Zeng, Z., Ga\u0161evi\u0107, D., & Liu, Z. (2024). Annotation guidelines-based knowledge augmentation: Towards enhancing large language models for educational text classification. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2406.00954","DOI":"10.48550\/arXiv.2406.00954"},{"key":"487_CR82","unstructured":"Livni, R., Shalev-Shwartz, S., & Shamir, O. (2014). On the computational efficiency of training neural networks. In Proceedings of the 28th international conference on neural information processing systems (Vol. 1, pp. 855\u2013863). MIT Press."},{"issue":"09","key":"487_CR83","doi-asserted-by":"publisher","first-page":"13389","DOI":"10.1609\/aaai.v34i09.7062","volume":"34","author":"J Lun","year":"2020","unstructured":"Lun, J., Zhu, J., Tang, Y., & Yang, M. (2020). Multiple data augmentation strategies for improving performance on automatic short answer scoring. Proceedings of the AAAI Conference on Artificial Intelligence, 34(09), 13389\u201313396. https:\/\/doi.org\/10.1609\/aaai.v34i09.7062","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"487_CR84","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1007\/s11280-022-01025-2","volume":"25","author":"KJ Madukwe","year":"2022","unstructured":"Madukwe, K. J., Gao, X., & Xue, B. (2022). Token replacement based data augmentation methods for hate speech detection. World Wide Web, 25, 1129\u20131150. https:\/\/doi.org\/10.1007\/s11280-022-01025-2","journal-title":"World Wide Web"},{"key":"487_CR85","doi-asserted-by":"publisher","unstructured":"Mao, Y., Mathias, L., Hou, R., Almahairi, A., Ma, H., Han, J., Yih, W.-T., & Khabsa, M. (2022). UNIPELT: A unified framework for parameter-efficient language model tuning. In S. Muresan, P. Nakov, & A. Villavicencio (Eds.), Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long Papers) (pp. 6253\u20136264). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.433","DOI":"10.18653\/v1\/2022.acl-long.433"},{"key":"487_CR86","doi-asserted-by":"publisher","first-page":"100423","DOI":"10.1016\/j.mlwa.2022.100423","volume":"10","author":"J Martinez-Gil","year":"2022","unstructured":"Martinez-Gil, J. (2022). A comprehensive review of stacking methods for semantic similarity measurement. Machine Learning with Applications, 10, 100423. https:\/\/doi.org\/10.1016\/j.mlwa.2022.100423","journal-title":"Machine Learning with Applications"},{"issue":"9","key":"487_CR87","doi-asserted-by":"publisher","first-page":"260","DOI":"10.3390\/fi14090260","volume":"14","author":"V Maslej-Kre\u0161\u0148\u00e1kov\u00e1","year":"2022","unstructured":"Maslej-Kre\u0161\u0148\u00e1kov\u00e1, V., Sarnovsk\u00fd, M., & Jackov\u00e1, J. (2022). Use of data augmentation techniques in detection of antisocial behavior using deep learning methods. Future Internet, 14(9), 260. https:\/\/doi.org\/10.3390\/fi14090260","journal-title":"Future Internet"},{"key":"487_CR88","unstructured":"Mitchell, T., Russell, T., Broomhead, P., & Aldridge, N. (2019). Towards robust computerised marking of free-text responses [Repository record]. Loughborough University's Institutional Repository. https:\/\/hdl.handle.net\/2134\/1884"},{"issue":"2","key":"487_CR89","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.","journal-title":"Research Methods in Applied Linguistics"},{"issue":"2","key":"487_CR90","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","volume":"35","author":"A Mohammed","year":"2023","unstructured":"Mohammed, A., & Kora, R. (2023). A comprehensive review on ensemble deep learning: Opportunities and challenges. Journal of King Saud University-Computer and Information Sciences, 35(2), 757\u2013774.","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"487_CR91","unstructured":"Mohler, M., Bunescu, R., & Mihalcea, R. (2011). Learning to grade short answer questions using semantic similarity measures and dependency graph alignments. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies (pp. 752\u2013762). Association for Computational Linguistics. https:\/\/aclanthology.org\/P11-1076.pdf"},{"key":"487_CR92","doi-asserted-by":"crossref","unstructured":"Ndukwe, I. G., Daniel, B. K., spsampsps Amadi, C. E. (2019). A machine learning grading system using chatbots. International conference on artificial intelligence in education (pp. 365\u2013368). Springer.","DOI":"10.1007\/978-3-030-23207-8_67"},{"key":"487_CR93","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1613\/jair.614","volume":"11","author":"D Opitz","year":"1999","unstructured":"Opitz, D., & Maclin, R. (1999). Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169\u2013198.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"487_CR94","doi-asserted-by":"publisher","unstructured":"Ormerod, C., Lottridge, S., Harris, A. E., Patel, M., van Wamelen, P., Kodeswaran, B., ... & Young, M. (2023). Automated short answer scoring using an ensemble of neural networks and latent semantic analysis classifiers. International Journal of Artificial Intelligence in Education, 33(3), 467-496.\u00a0https:\/\/doi.org\/10.1007\/s40593-022-00294-2","DOI":"10.1007\/s40593-022-00294-2"},{"key":"487_CR95","unstructured":"Ormerod, C. (2022). Short-answer scoring with ensembles of pretrained language models. Preprint retrieved from https:\/\/arxiv.org\/abs\/2202.11558"},{"issue":"12","key":"487_CR96","doi-asserted-by":"publisher","first-page":"5803","DOI":"10.3390\/app12125803","volume":"12","author":"YH Park","year":"2022","unstructured":"Park, Y. H., Choi, Y. S., Park, C. Y., & Lee, K. J. (2022). EssayGAN: Essay data augmentation based on generative adversarial networks for automated essay scoring. Applied Sciences, 12(12), 5803. https:\/\/doi.org\/10.3390\/app12125803","journal-title":"Applied Sciences"},{"key":"487_CR97","doi-asserted-by":"publisher","unstructured":"Prabhudesai, A., & Duong, T. N. (2019). Automatic short answer grading using Siamese bidirectional LSTM based regression. In 2019 IEEE international conference on engineering, technology and education (TALE) (pp. 1-6). IEEE, Yogyakarta, Indonesia, 10-13 December 2019. https:\/\/doi.org\/10.1109\/TALE48000.2019.9226026","DOI":"10.1109\/TALE48000.2019.9226026"},{"key":"487_CR98","doi-asserted-by":"publisher","unstructured":"Prasain, B., & Bajaj, S. K. (2020, November). Analysis of algorithms in automated marking in education: A proposed hybrid algorithm. In 2020 5th international conference on innovative technologies in intelligent systems and industrial applications (CITISIA)\u00a0(pp. 1-10). IEEE, Sydney, Australia, 25-27 November 2020. https:\/\/doi.org\/10.1109\/CITISIA50690.2020.9371783","DOI":"10.1109\/CITISIA50690.2020.9371783"},{"key":"487_CR99","doi-asserted-by":"publisher","unstructured":"Proskura, P., & Zaytsev, A. (2022). Effective training-time stacking for ensembling of deep neural networks. In Proceedings of the 2022 5th international conference on artificial intelligence and pattern recognition (AIPR 2022) (pp. 1\u20139). Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3573942.3573954","DOI":"10.1145\/3573942.3573954"},{"issue":"1","key":"487_CR100","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/ai4010004","volume":"4","author":"A Rahali","year":"2023","unstructured":"Rahali, A., & Akhloufi, M. A. (2023). End-to-end transformer-based models in textual-based NLP. Ai, 4(1), 54\u2013110. https:\/\/doi.org\/10.3390\/ai4010004","journal-title":"Ai"},{"key":"487_CR101","doi-asserted-by":"publisher","unstructured":"Ramesh, D., & Sanampudi, S. K. (2022). An automated essay scoring systems: A systematic literature review. Artificial Intelligence Review, 55(3), 2495\u20132527. https:\/\/doi.org\/10.1007\/s10462-021-10068-2","DOI":"10.1007\/s10462-021-10068-2"},{"key":"487_CR102","doi-asserted-by":"publisher","first-page":"5573","DOI":"10.1007\/s10639-021-10838-z","volume":"27","author":"V Ramnarain Seetohul","year":"2022","unstructured":"Ramnarain-Seetohul, V., Bassoo, V., & Rosunally, Y. (2022). Similarity measures in automated essay scoring systems: A ten year review. Education and Information Technologies, 27, 5573\u20135604. https:\/\/doi.org\/10.1007\/s10639-021-10838-z","journal-title":"Education and Information Technologies"},{"issue":"40","key":"487_CR103","first-page":"651","volume":"9","author":"S Ramraj","year":"2016","unstructured":"Ramraj, S., Uzir, N., Sunil, R., & Banerjee, S. (2016). Experimenting XGBoost algorithm for prediction and classification of different datasets. International Journal of Control Theory and Applications, 9(40), 651\u2013662.","journal-title":"International Journal of Control Theory and Applications"},{"key":"487_CR104","unstructured":"Ranasinghe, T. (2022). Deep learning based semantic textual similarity for applications in translation technology. Doctoral dissertation, University of Wolverhampton. Wolverhampton Research Repository. http:\/\/hdl.handle.net\/2436\/624530. Retrieved November 4, 2024"},{"key":"487_CR105","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1007\/s10462-018-9670-y","volume":"52","author":"S Rani","year":"2019","unstructured":"Rani, S., & Kumar, P. (2019). A journey of Indian languages over sentiment analysis: A systematic review. Artificial Intelligence Review, 52, 1415\u20131462. https:\/\/doi.org\/10.1007\/s10462-018-9670-y","journal-title":"Artificial Intelligence Review"},{"key":"487_CR106","doi-asserted-by":"publisher","first-page":"119594","DOI":"10.1016\/j.eswa.2023.119594","volume":"217","author":"S Rao","year":"2023","unstructured":"Rao, S., Verma, A. K., & Bhatia, T. (2023). Hybrid ensemble framework with self-attention mechanism for social spam detection on imbalanced data. Expert Systems with Applications, 217, 119594. https:\/\/doi.org\/10.1016\/j.eswa.2023.119594","journal-title":"Expert Systems with Applications"},{"key":"487_CR107","doi-asserted-by":"crossref","unstructured":"Re, M., & Valentini, G. (2012). Ensemble methods: a review. In advances in machine learning and data mining for astronomy (pp. 563\u2013594). Chapman & Hall.","DOI":"10.1201\/b11822-34"},{"key":"487_CR108","doi-asserted-by":"crossref","unstructured":"Reimers, N., & Gurevych, I. (2019, 11 8). Sentence-BERT: Sentence embeddings using siamese BERT-networks. Proceedings of the 2019 conference on empirical methods in natural language processing. association for computational linguistics. Retrieved from S-BERT.net, Sentence transformers: Preprint retrieved from https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"487_CR109","unstructured":"Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Gupta, B. B., . . . Wang, X. (2021). A survey of deep active learning. Preprint retrieved from https:\/\/arxiv.org\/abs\/2009.00236"},{"key":"487_CR110","unstructured":"Resnik, P., Niv, M., Nossal, M., Schnitzer, G., Stoner, J., Kapit, A., & Toren, R. (2006). Using intrinsic and extrinsic metrics to evaluate accuracy and facilitation in computer-assisted coding. In Perspectives in health information management, computer-assisted coding conference proceedings. Retrieved December 28, 2024, from https:\/\/pdfs.semanticscholar.org\/6b74\/584fc708ca77de50c0973f6fd9fdee37fe43.pdf"},{"key":"487_CR111","doi-asserted-by":"publisher","unstructured":"Saeed, M. M., & Gomaa, W. H. (2022). An ensemble-based model to improve the accuracy of automatic short answer grading. In\u00a02022 2nd international mobile, intelligent, and ubiquitous computing conference (MIUCC)\u00a0(pp. 337-342). IEEE, Cairo, Egypt, 08-09 May 2022.https:\/\/doi.org\/10.1109\/MIUCC55081.2022.9781737","DOI":"10.1109\/MIUCC55081.2022.9781737"},{"issue":"25","key":"487_CR112","doi-asserted-by":"publisher","first-page":"4845","DOI":"10.1007\/s10639-020-10192-6","volume":"25","author":"S Saha","year":"2020","unstructured":"Saha, S., & Gupta, R. (2020). Adopting computer-assisted assessment in evaluation of handwritten answer books: An experimental study. Education and Information Technologies, 25(25), 4845\u20134860. https:\/\/doi.org\/10.1007\/s10639-020-10192-6","journal-title":"Education and Information Technologies"},{"issue":"1","key":"487_CR113","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TLT.2019.2897997","volume":"13","author":"A Sahu","year":"2020","unstructured":"Sahu, A., & Bhowmick, P. K. (2020). Feature engineering and ensemble-based approach for improving automatic short-answer grading performance. IEEE Transactions on Learning Technologies, 13(1), 77\u201390. https:\/\/doi.org\/10.1109\/TLT.2019.2897997","journal-title":"IEEE Transactions on Learning Technologies"},{"issue":"6","key":"487_CR114","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-021-00815-1","volume":"2","author":"IH Sarker","year":"2021","unstructured":"Sarker, I. H. (2021). Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2(6), 1\u201320. https:\/\/doi.org\/10.1007\/s42979-021-00815-1","journal-title":"SN Computer Science"},{"key":"487_CR115","unstructured":"Sasse, L., Nicolaisen-Sobesky, E., Dukart, J., Eickhoff, S., G\u00f6tz, M., Hamdan, S., . . . Patil, K. (2024). On leakage in machine learning pipelines. Preprint retrieved from https:\/\/arxiv.org\/abs\/2311.04179"},{"key":"487_CR116","doi-asserted-by":"publisher","unstructured":"Schlippe, T., Stierstorfer, Q., Koppel, M. T., & Libbrecht, P. (2022). Explainability in automatic short answer grading. In E. Cheng, T. Wang, T. Schlippe, & G. Beligiannis (Eds.), Artificial intelligence in education technologies: New development and innovative practices (pp. 71\u201386). Springer. https:\/\/doi.org\/10.1007\/978-981-19-8040-4_5","DOI":"10.1007\/978-981-19-8040-4_5"},{"key":"487_CR117","doi-asserted-by":"publisher","unstructured":"Schneider, J., Schenk, B., & Niklaus, C. (2024). Towards LLM-based autograding for short textual answers. In Proceedings of the 16th international conference on computer supported education (CSEDU 2024) (Vol. 1, pp. 280\u2013288). SCITEPRESS. https:\/\/doi.org\/10.5220\/0012552200003693","DOI":"10.5220\/0012552200003693"},{"key":"487_CR118","doi-asserted-by":"publisher","first-page":"118517","DOI":"10.1016\/j.eswa.2022.118517","volume":"212","author":"S Sendhilkumar","year":"2023","unstructured":"Sendhilkumar, S. (2023). Developing a conceptual framework for short text categorization using hybrid CNN-LSTM based Caledonian crow optimization. Expert Systems with Applications, 212, 118517. https:\/\/doi.org\/10.1016\/j.eswa.2022.118517","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"487_CR119","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3102\/0034654307313795","volume":"78","author":"V Shute","year":"2008","unstructured":"Shute, V. (2008). Focus on formative feedback. Review of Educational Research, 78(1), 153\u2013189. https:\/\/doi.org\/10.3102\/0034654307313795","journal-title":"Review of Educational Research"},{"key":"487_CR120","unstructured":"Siddiqi, R., & Harrison, C. J. (2008). On the automated assessment of short free-text responses. In Paper presented at the 34th international association for educational assessment (IAEA) annual conference."},{"key":"487_CR121","doi-asserted-by":"publisher","unstructured":"Simon, S., Kolyada, N., Akiki, C., Potthast, M., Stein, B., & Siegmund, N. (2023). Exploring hyperparameter usage and tuning in machine learning research. In Proceedings of the IEEE\/ACM 2nd international conference on AI engineering - software engineering for AI (CAIN) (pp. 68\u201379). IEEE. https:\/\/doi.org\/10.1109\/CAIN58948.2023.00016","DOI":"10.1109\/CAIN58948.2023.00016"},{"key":"487_CR122","doi-asserted-by":"crossref","unstructured":"Sonkar, S., Ni, K., Lu, L. T., Kincaid, K., Hutchinson, J. S., spsampsps Baraniuk, R. G. (2024). Automated long answer grading with RiceChem dataset. Preprint retrieved from https:\/\/arxiv.org\/abs\/2404.14316","DOI":"10.1007\/978-3-031-64302-6_12"},{"key":"487_CR123","unstructured":"Steimel, K., & Riordan, B. (2020). Towards instance-based content scoring with pre-trained transformer models. In Proceedings of the Thirty-fourth AAAI conference on artificial intelligence (AAAI-20). AAAI Press."},{"issue":"4","key":"487_CR124","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1504\/IJBRA.2010.036001","volume":"6","author":"S Stoutenburg","year":"2010","unstructured":"Stoutenburg, S., Kalita, J., Ewing, K., & Hines, L. (2010). Scaling alignment of large ontologies. International Journal of Bioinformatics Research and Applications, 6(4), 384\u2013401. https:\/\/doi.org\/10.1504\/IJBRA.2010.036001","journal-title":"International Journal of Bioinformatics Research and Applications"},{"key":"487_CR125","doi-asserted-by":"crossref","unstructured":"Sukkarieh, J. Z., & Pulman, S. G. (2005). automatic short answer marking. Proceedings of the 2nd workshop on building educational applications using NLP (pp. 9\u201316). Association for Computational Linguistics.","DOI":"10.3115\/1609829.1609831"},{"key":"487_CR126","unstructured":"Sukkarieh, J. Z., Pulman, S. G., & Raikes, N. (2003). Auto-marking: Using computational linguistics to score short, free text responses. In Proceedings of the 29th annual conference of the international association for educational assessment."},{"key":"487_CR127","unstructured":"Sukkarieh, J. Z., Pulman, S. G., & Raikes, N. (2004). Auto-marking2: An update on the UCLES-OXFORD University research into using computational linguistics to score short, free text responses. In Paper presented at the 30th annual conference of the international association for educational assessment (IAEA)."},{"key":"487_CR128","doi-asserted-by":"publisher","unstructured":"Sung, C., Dhamecha, T., & Mukhi, N. (2019). Improving short answer grading using transformer-based pre-training. In S. Isotani, E. Mill\u00e1n, A. Ogan, P. Hastings, B. McLaren, & R. Luckin (Eds.), Artificial intelligence in education: 20th international conference, AIED 2019, proceedings (pp. 503\u2013509). Springer. https:\/\/doi.org\/10.1007\/978-3-030-23204-7_39","DOI":"10.1007\/978-3-030-23204-7_39"},{"key":"487_CR129","doi-asserted-by":"crossref","unstructured":"Suzen, N., Gorban, A., Levesley, J., & Mirkes, E. (2020). Automatic short answer grading and feedback using text mining methods. Procedia computer science, 169, 726\u2013743. Preprint retrieved from https:\/\/arxiv.org\/abs\/1807.10543","DOI":"10.1016\/j.procs.2020.02.171"},{"key":"487_CR130","doi-asserted-by":"publisher","unstructured":"Tashu, T. M., & Horv\u00e1th, T. (2020). Smartscore-short answer scoring made easy using sem-LSH. In\u00a02020 IEEE 14th international conference on semantic computing (ICSC) (pp. 145-149). IEEE, San Diego, CA, USA, 03-05 February 2020.https:\/\/doi.org\/10.1109\/ICSC.2020.00028","DOI":"10.1109\/ICSC.2020.00028"},{"key":"487_CR131","doi-asserted-by":"publisher","unstructured":"Tashu, T. M., Maurya, C. K., & Horv\u00e1th, T. (2022). Deep learning architecture for automatic essay scoring. Preprint retrieved from https:\/\/arxiv.org\/abs\/2206.08232. https:\/\/doi.org\/10.48550\/arXiv.2206.08232","DOI":"10.48550\/arXiv.2206.08232"},{"issue":"11","key":"487_CR132","doi-asserted-by":"publisher","first-page":"13407","DOI":"10.1007\/s10462-023-10472-w","volume":"56","author":"D Tiwari","year":"2023","unstructured":"Tiwari, D., Nagpal, B., Bhati, B. S., Mishra, A., & Kumar, M. (2023). A systematic review of social network sentiment analysis with comparative study of ensemble-based techniques. Artificial Intelligence Review, 56(11), 13407\u201313461. https:\/\/doi.org\/10.1007\/s10462-023-10472-w","journal-title":"Artificial Intelligence Review"},{"key":"487_CR133","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... Polosukhin, I. (2017). Attention is all you need. Preprint retrieved from https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"487_CR134","doi-asserted-by":"publisher","first-page":"3039","DOI":"10.4028\/www.scientific.net\/AMR.753-755.3039","volume":"753\u2013755","author":"N Wang","year":"2013","unstructured":"Wang, N., Xu, L., Li, L., & Xu, L. (2013). Design and implementation of an automatic scoring subjective question system based on domain ontology. Advanced Materials Research Online, 753\u2013755, 3039\u20133042. https:\/\/doi.org\/10.4028\/www.scientific.net\/AMR.753-755.3039","journal-title":"Advanced Materials Research Online"},{"issue":"2","key":"487_CR135","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/S11336-012-9258-4","volume":"77","author":"MJ Warrens","year":"2012","unstructured":"Warrens, M. J. (2012). Some paradoxical results for the quadratically weighted kappa. Psychometrika, 77(2), 315\u2013323. https:\/\/doi.org\/10.1007\/S11336-012-9258-4","journal-title":"Psychometrika"},{"key":"487_CR136","doi-asserted-by":"publisher","unstructured":"Wei, J., & Zou, K. (2019). EDA: Easy data augmentation techniques for boosting performance on text classification tasks. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (pp. 6382\u20136388). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"issue":"11","key":"487_CR137","doi-asserted-by":"publisher","first-page":"4532","DOI":"10.3390\/app14114532","volume":"14","author":"MC Wijanto","year":"2024","unstructured":"Wijanto, M. C., & Yong, H. S. (2024). Combining balancing dataset and sentencetransformers to improve short answer grading performance. Applied Sciences, 14(11), 4532. https:\/\/doi.org\/10.3390\/app14114532","journal-title":"Applied Sciences"},{"key":"487_CR138","doi-asserted-by":"publisher","unstructured":"Wong, Y. K. (2021). The difference of machine learning and deep learning algorithms. In Proceedings of the 3rd international conference on machine learning & applications (CMLA 2021) (pp. 249\u2013257). AIRCC Publishing Corporation. https:\/\/doi.org\/10.5121\/csit.2021.111519","DOI":"10.5121\/csit.2021.111519"},{"key":"487_CR139","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","volume":"63","author":"Q XiPeng","year":"2020","unstructured":"XiPeng, Q., TianXiang, S., YiGe, X., YunFan, S., Ning, D., & XuanJing, H. (2020). Pre-trained models for natural language processing: A survey. Science China Technological Sciences, 63, 1872\u20131897. https:\/\/doi.org\/10.1007\/s11431-020-1647-3","journal-title":"Science China Technological Sciences"},{"key":"487_CR140","unstructured":"Yoon, S.-Y. (2023). Short answer grading using one-shot prompting and text similarity scoring model. Preprint retrieved from https:\/\/arxiv.org\/abs\/2305.18638"},{"issue":"1","key":"487_CR141","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1111\/emip.12544","volume":"42","author":"T Zesch","year":"2023","unstructured":"Zesch, T., & Horbach, A. (2023). To score or not to score: Factors influencing performance and feasibility of automatic content scoring of text responses. Educational Measurement: Issues and Practice, 42(1), 44\u201358.","journal-title":"Educational Measurement: Issues and Practice"},{"issue":"1","key":"487_CR142","doi-asserted-by":"publisher","first-page":"9336298","DOI":"10.1155\/2022\/9336298","volume":"2022","author":"F Zhang","year":"2022","unstructured":"Zhang, F., Yu, L., & Shen, J. (2022). Automatic scoring of english essays based on machine learning technology in a wireless network environment. Security and Communication Networks, 2022(1), 9336298. https:\/\/doi.org\/10.1155\/2022\/9336298","journal-title":"Security and Communication Networks"},{"key":"487_CR143","doi-asserted-by":"crossref","unstructured":"Zhao, C., Silva, M., & Poulsen, S. (2025). Language models are few-shot graders. Preprint retrieved from https:\/\/arxiv.org\/abs\/2502.13337","DOI":"10.1007\/978-3-031-98459-4_1"},{"key":"487_CR144","doi-asserted-by":"publisher","DOI":"10.1201\/b12207","volume-title":"Ensemble methods foundations and algorithms","author":"Z-H Zhou","year":"2012","unstructured":"Zhou, Z.-H. (2012). Ensemble methods foundations and algorithms. Chapman & Hall."},{"issue":"10","key":"487_CR145","doi-asserted-by":"publisher","first-page":"5870","DOI":"10.3390\/app13105870","volume":"13","author":"F Zhou","year":"2023","unstructured":"Zhou, F., Fan, H., Liu, Y., Zhang, H., & Ji, R. (2023). Hybrid model of machine learning method and empirical method for rate of penetration prediction based on data similarity. Applied Sciences, 13(10), 5870. https:\/\/doi.org\/10.3390\/app13105870","journal-title":"Applied Sciences"},{"key":"487_CR146","doi-asserted-by":"publisher","unstructured":"Zhua, M., Liu, O. L., & Lee, H.-S. (2020). The effect of automated feedback on revision behavior and learning gains in formative assessment of scientific argument writing. Computers & Education, 143. https:\/\/doi.org\/10.1016\/j.compedu.2019.103668","DOI":"10.1016\/j.compedu.2019.103668"},{"issue":"3","key":"487_CR147","doi-asserted-by":"publisher","first-page":"239","DOI":"10.3233\/FI-2020-1904","volume":"172","author":"K Zupanc","year":"2020","unstructured":"Zupanc, K., & Bosni\u0107, Z. (2020). Improvement of automated essay grading by grouping similar graders. Fundamenta Informaticae, 172(3), 239\u2013259. https:\/\/doi.org\/10.3233\/FI-2020-1904","journal-title":"Fundamenta Informaticae"}],"container-title":["International Journal of Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-025-00487-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40593-025-00487-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-025-00487-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:12:43Z","timestamp":1772647963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40593-025-00487-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":147,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["487"],"URL":"https:\/\/doi.org\/10.1007\/s40593-025-00487-5","relation":{},"ISSN":["1560-4292","1560-4306"],"issn-type":[{"value":"1560-4292","type":"print"},{"value":"1560-4306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,16]]},"assertion":[{"value":"17 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 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":"Competing interests The authors declare no competing interests","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}