{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:06:52Z","timestamp":1765807612844,"version":"3.48.0"},"reference-count":118,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004040","name":"KU Leuven","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012331","name":"Flanders Innovation & Entrepreneurship","doi-asserted-by":"publisher","award":["HBC.2022.0164"],"award-info":[{"award-number":["HBC.2022.0164"]}],"id":[{"id":"10.13039\/100012331","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Education: Artificial Intelligence"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1016\/j.caeai.2025.100414","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T07:55:51Z","timestamp":1747122951000},"page":"100414","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Opportunities of natural language processing for comparative judgment assessment of essays"],"prefix":"10.1016","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4697-0270","authenticated-orcid":false,"given":"Michiel","family":"De Vrindt","sequence":"first","affiliation":[]},{"given":"Ana\u00efs","family":"Tack","sequence":"additional","affiliation":[]},{"given":"Wim","family":"Van den Noortgate","sequence":"additional","affiliation":[]},{"given":"Marije","family":"Lesterhuis","sequence":"additional","affiliation":[]},{"given":"Renske","family":"Bouwer","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.caeai.2025.100414_br0010","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MC.2020.2996587","article-title":"A research agenda for hybrid intelligence: Augmenting human intellect with collaborative, adaptive, responsible, and explainable artificial intelligence","volume":"53","author":"Akata","year":"2020","journal-title":"Computer"},{"key":"10.1016\/j.caeai.2025.100414_br0020","series-title":"2021 international conference on innovation and intelligence for informatics, computing, and technologies (3ICT)","first-page":"403","article-title":"AI and machine learning techniques in the development of intelligent tutoring system: A review","author":"AlShaikh","year":"2021"},{"key":"10.1016\/j.caeai.2025.100414_br0030","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1111\/j.1468-2389.2009.00479.x","article-title":"The mediating role of feedback acceptance in the relationship between feedback and attitudinal and performance outcomes","volume":"17","author":"Anseel","year":"2009","journal-title":"International Journal of Selection and Assessment"},{"key":"10.1016\/j.caeai.2025.100414_br0040","doi-asserted-by":"crossref","first-page":"24","DOI":"10.21061\/jots.v45i1.a.3","article-title":"Using adaptive comparative judgment in writing assessment","volume":"45","author":"Baniya","year":"2019","journal-title":"The Journal of Technology Studies"},{"key":"10.1016\/j.caeai.2025.100414_br0050","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s10798-018-9442-7","article-title":"Using adaptive comparative judgment for student formative feedback and learning during a middle school design project","volume":"29","author":"Bartholomew","year":"2019","journal-title":"International Journal of Technology and Design Education"},{"key":"10.1016\/j.caeai.2025.100414_br0060","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1162\/tacl_a_00236","article-title":"Powergrading: A clustering approach to amplify human effort for short answer grading","volume":"1","author":"Basu","year":"2013","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.caeai.2025.100414_br0070","series-title":"Proceedings of the 11th workshop on innovative use of NLP for building educational applications","first-page":"63","article-title":"Topicality-based indices for essay scoring","author":"Beigman Klebanov","year":"2016"},{"key":"10.1016\/j.caeai.2025.100414_br0080","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0095693","article-title":"The exploration-exploitation dilemma: A multidisciplinary framework","volume":"9","author":"Berger-Tal","year":"2014","journal-title":"PLoS ONE"},{"key":"10.1016\/j.caeai.2025.100414_br0090","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1111\/j.1745-459X.2003.tb00373.x","article-title":"Agreement and reliability assessments for performance of sensory descriptive panel","volume":"18","author":"Bi","year":"2003","journal-title":"Journal of Sensory Studies"},{"key":"10.1016\/j.caeai.2025.100414_br0100","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/02602930801955978","article-title":"Marking and moderation in the UK: False assumptions and wasted resources","volume":"34","author":"Bloxham","year":"2009","journal-title":"Assessment Evaluation Higher Education"},{"key":"10.1016\/j.caeai.2025.100414_br0110","series-title":"Intelligent tutoring systems","first-page":"68","article-title":"SHAPed automated essay scoring: Explaining writing features' contributions to English writing organization","author":"Boulanger","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br0120","doi-asserted-by":"crossref","first-page":"497","DOI":"10.17239\/jowr-2024.15.03.03","article-title":"Comparative approaches to the assessment of writing: Reliability and validity of benchmark rating and comparative judgement","volume":"15","author":"Bouwer","year":"2023","journal-title":"Journal of Writing Research"},{"key":"10.1016\/j.caeai.2025.100414_br0130","first-page":"324","article-title":"Rank analysis of incomplete block designs: I. the method of paired comparisons","volume":"39","author":"Bradley","year":"1952","journal-title":"Biometrika"},{"key":"10.1016\/j.caeai.2025.100414_br0140","series-title":"Techniques for monitoring the comparability of examination standards. Qualifications and curriculum","first-page":"246","article-title":"Paired comparison methods","author":"Bramley","year":"2007"},{"year":"2015","series-title":"Investigating the reliability of adaptive comparative judgment","author":"Bramley","key":"10.1016\/j.caeai.2025.100414_br0150"},{"key":"10.1016\/j.caeai.2025.100414_br0160","first-page":"14","article-title":"Assessing changes in standards over time using thurstone paired comparisons","volume":"25","author":"Bramley","year":"1998","journal-title":"Education Research and Perspectives"},{"key":"10.1016\/j.caeai.2025.100414_br0170","first-page":"43","article-title":"The effect of adaptivity on the reliability coefficient in adaptive comparative judgement","volume":"26","author":"Bramley","year":"2019","journal-title":"Assessment in Education: Principles, Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br0180","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/08957347.2011.532417","article-title":"Generalizability theory and classical test theory","volume":"24","author":"Brennan","year":"2010","journal-title":"Applied Measurement in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0190","series-title":"Proceedings of the first ACM conference on learning @ scale conference","first-page":"89","article-title":"Divide and correct: Using clusters to grade short answers at scale","author":"Brooks","year":"2014"},{"key":"10.1016\/j.caeai.2025.100414_br0200","series-title":"Fundamentals of artificial intelligence","first-page":"603","article-title":"Natural language processing","author":"Chowdhary","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br0210","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1080\/0960085X.2018.1445461","article-title":"An information system design theory for the comparative judgement of competences","volume":"27","author":"Coenen","year":"2018","journal-title":"European Journal of Information Systems"},{"key":"10.1016\/j.caeai.2025.100414_br0220","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educational and Psychological Measurement"},{"key":"10.1016\/j.caeai.2025.100414_br0230","doi-asserted-by":"crossref","first-page":"37","DOI":"10.18608\/jla.2023.7801","article-title":"The effects of explanations in automated essay scoring systems on student trust and motivation","volume":"10","author":"Conijn","year":"2023","journal-title":"Journal of Learning Analytics"},{"key":"10.1016\/j.caeai.2025.100414_br0240","doi-asserted-by":"crossref","first-page":"316","DOI":"10.3102\/1076998619890589","article-title":"Adaptive pairwise comparison for educational measurement","volume":"45","author":"Crompvoets","year":"2020","journal-title":"Journal of Educational and Behavioral Statistics"},{"year":"2020","series-title":"Making a choice is not easy?! Unravelling the task difficulty of comparative judgement to assess student work","author":"van Daal","key":"10.1016\/j.caeai.2025.100414_br0250"},{"key":"10.1016\/j.caeai.2025.100414_br0260","first-page":"59","article-title":"Validity of comparative judgement to assess academic writing: Examining implications of its holistic character and building on a shared consensus","volume":"26","author":"van Daal","year":"2016","journal-title":"Assessment in Education: Principles Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br0270","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/feduc.2017.00044","article-title":"The complexity of assessing student work using comparative judgment: The moderating role of decision accuracy","volume":"2","author":"van Daal","year":"2017","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0280","doi-asserted-by":"crossref","first-page":"132","DOI":"10.3389\/feduc.2022.854378","article-title":"Text mining to alleviate the cold-start problem of adaptive comparative judgments","volume":"7","author":"De Vrindt","year":"2022","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0290","series-title":"Proceedings of the 19th workshop on innovative use of NLP for building educational applications (BEA 2024)","first-page":"125","article-title":"Predicting initial essay quality scores to increase the efficiency of comparative judgment assessments","author":"De Vrindt","year":"2024"},{"key":"10.1016\/j.caeai.2025.100414_br0300","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.asw.2014.03.006","article-title":"Automated essay scoring feedback for second language writers: How does it compare to instructor feedback?","volume":"22","author":"Dikli","year":"2014","journal-title":"Assessing Writing"},{"key":"10.1016\/j.caeai.2025.100414_br0310","series-title":"Findings of the association for computational linguistics: ACL 2023","first-page":"1538","article-title":"Prompt- and trait relation-aware cross-prompt essay trait scoring","author":"Do","year":"2023"},{"key":"10.1016\/j.caeai.2025.100414_br0320","series-title":"Proceedings of the 21st conference on computational natural language learning (CoNLL 2017)","first-page":"153","article-title":"Attention-based recurrent convolutional neural network for automatic essay scoring","author":"Dong","year":"2017"},{"author":"Dong","key":"10.1016\/j.caeai.2025.100414_br0330"},{"key":"10.1016\/j.caeai.2025.100414_br0340","series-title":"Proceedings of the second (2015) ACM conference on learning @ scale","first-page":"3","article-title":"Effective sampling for large-scale automated writing evaluation systems","author":"Dronen","year":"2015"},{"year":"1997","series-title":"Comparability studies between modular and non-modular syllabuses in gce advanced level biology, English literature and mathematics in the 1996 summer examinations","author":"D'Arcy","key":"10.1016\/j.caeai.2025.100414_br0350"},{"key":"10.1016\/j.caeai.2025.100414_br0360","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1111\/emip.12537","article-title":"Using active learning methods to strategically select essays for automated scoring","volume":"42","author":"Firoozi","year":"2023","journal-title":"Educational Measurement, Issues and Practice"},{"key":"10.1016\/j.caeai.2025.100414_br0370","series-title":"Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers)","first-page":"549","article-title":"Coarse-grained argumentation features for scoring persuasive essays","author":"Ghosh","year":"2016"},{"key":"10.1016\/j.caeai.2025.100414_br0380","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/feduc.2020.582800","article-title":"The complexity of comparative judgments in assessing argumentative writing: An eye tracking study","volume":"5","author":"Gijsen","year":"2021","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0390","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s10648-012-9192-0","article-title":"Learning from comparing multiple examples: On the dilemma of \u201csimilar\u201d or \u201cdifferent\u201d","volume":"24","author":"Guo","year":"2012","journal-title":"Educational Psychology Review"},{"key":"10.1016\/j.caeai.2025.100414_br0400","series-title":"International conference on artificial intelligence in education","first-page":"140","article-title":"Active learning for improving machine learning of student explanatory essays","author":"Hastings","year":"2018"},{"key":"10.1016\/j.caeai.2025.100414_br0410","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3102\/003465430298487","article-title":"The power of feedback","volume":"77","author":"Hattie","year":"2007","journal-title":"Review of Educational Research"},{"key":"10.1016\/j.caeai.2025.100414_br0420","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF03216919","article-title":"Using the method of pairwise comparison to obtain reliable teacher assessments","volume":"37","author":"Heldsinger","year":"2010","journal-title":"The Australian Educational Researcher"},{"key":"10.1016\/j.caeai.2025.100414_br0430","series-title":"Proceedings of the 11th workshop on innovative use of NLP for building educational applications","first-page":"301","article-title":"Investigating active learning for short-answer scoring","author":"Horbach","year":"2016"},{"key":"10.1016\/j.caeai.2025.100414_br0440","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.asw.2019.04.002","article-title":"Raters' perceptions of assessment criteria relevance","volume":"41","author":"Humphry","year":"2019","journal-title":"Assessing Writing"},{"key":"10.1016\/j.caeai.2025.100414_br0450","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1002\/berj.3519","article-title":"Measuring conceptual understanding in randomised controlled trials: Can comparative judgement help?","volume":"45","author":"Jones","year":"2019","journal-title":"British Educational Research Journal"},{"key":"10.1016\/j.caeai.2025.100414_br0460","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s10649-015-9607-1","article-title":"The problem of assessing problem solving: Can comparative judgement help?","volume":"89","author":"Jones","year":"2015","journal-title":"Educational Studies in Mathematics"},{"key":"10.1016\/j.caeai.2025.100414_br0470","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1080\/02602938.2013.875117","article-title":"Rubrics as a way of providing transparency in assessment","volume":"39","author":"Jonsson","year":"2014","journal-title":"Assessment Evaluation Higher Education"},{"key":"10.1016\/j.caeai.2025.100414_br0480","series-title":"Proceedings of the twenty-eighth international joint conference on artificial intelligence","first-page":"6300","article-title":"Automated essay scoring: A survey of the state of the art","author":"Ke","year":"2019"},{"key":"10.1016\/j.caeai.2025.100414_br0490","first-page":"1","article-title":"Critiquing the rationales for using comparative judgement: A call for clarity","volume":"29","author":"Kelly","year":"2022","journal-title":"Assessment in Education: Principles, Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br0500","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s11336-011-9238-0","article-title":"A note on the reliability coefficients for item response model-based ability estimates","volume":"77","author":"Kim","year":"2012","journal-title":"Psychometrika"},{"key":"10.1016\/j.caeai.2025.100414_br0510","doi-asserted-by":"crossref","DOI":"10.3389\/feduc.2020.572367","article-title":"Explainable automated essay scoring: Deep learning really has pedagogical value","volume":"5","author":"Kumar","year":"2020","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0520","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1007\/s40593-020-00211-5","article-title":"Automated essay scoring and the deep learning black box: How are rubric scores determined?","volume":"31","author":"Kumar","year":"2021","journal-title":"International Journal of Artificial Intelligence in Education"},{"year":"2003","series-title":"Human judgment: The eye of the beholder","author":"Laming","key":"10.1016\/j.caeai.2025.100414_br0530"},{"key":"10.1016\/j.caeai.2025.100414_br0540","doi-asserted-by":"crossref","first-page":"106","DOI":"10.3389\/feduc.2022.784261","article-title":"Assessing the quality of argumentative texts: Examining the general agreement between different rating procedures and exploring inferences of (dis) agreement cases","volume":"7","author":"Landrieu","year":"2022","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0550","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1177\/0265532220929918","article-title":"Automated scoring of junior and senior high essays using coh-metrix features: Implications for large-scale language testing","volume":"38","author":"Latifi","year":"2021","journal-title":"Language Testing"},{"key":"10.1016\/j.caeai.2025.100414_br0560","series-title":"Proceedings of the 31st international conference on machine learning","first-page":"1188","article-title":"Distributed representations of sentences and documents","author":"Le","year":"2014"},{"key":"10.1016\/j.caeai.2025.100414_br0570","doi-asserted-by":"crossref","first-page":"1","DOI":"10.17239\/L1ESLL-2018.18.01.02","article-title":"When teachers compare argumentative texts: Decisions informed by multiple complex aspects of text quality","volume":"18","author":"Lesterhuis","year":"2018","journal-title":"L1-Educational Studies in Language and Literature"},{"key":"10.1016\/j.caeai.2025.100414_br0580","doi-asserted-by":"crossref","first-page":"122","DOI":"10.3389\/feduc.2022.823895","article-title":"Validity of comparative judgment scores: How assessors evaluate aspects of text quality when comparing argumentative texts","volume":"7","author":"Lesterhuis","year":"2022","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0590","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MSP.2022.3153277","article-title":"Toward explainable artificial intelligence for regression models: A methodological perspective","volume":"39","author":"Letzgus","year":"2022","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.caeai.2025.100414_br0600","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106491","article-title":"Sednn: Shared and enhanced deep neural network model for cross-prompt automated essay scoring","volume":"210","author":"Li","year":"2020","journal-title":"Knowledge-Based Systems"},{"year":"1989","series-title":"Many-faceted Rasch measurement","author":"Linacre","key":"10.1016\/j.caeai.2025.100414_br0610"},{"key":"10.1016\/j.caeai.2025.100414_br0620","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1109\/TVCG.2017.2745141","article-title":"Visual exploration of semantic relationships in neural word embeddings","volume":"24","author":"Liu","year":"2017","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.caeai.2025.100414_br0630","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1037\/h0043178","article-title":"On the possible psychophysical laws","volume":"66","author":"Luce","year":"1959","journal-title":"Psychological Review"},{"key":"10.1016\/j.caeai.2025.100414_br0640","series-title":"Advances in neural information processing systems","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"10.1016\/j.caeai.2025.100414_br0650","doi-asserted-by":"crossref","first-page":"249","DOI":"10.13109\/buer.2021.74.3.249","article-title":"A short history, emerging challenges and co-operation structures for artificial intelligence in education","volume":"74","author":"Mavrikis","year":"2021","journal-title":"Bildung und Erziehung"},{"key":"10.1016\/j.caeai.2025.100414_br0660","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"883","article-title":"Jump-starting item parameters for adaptive language tests","author":"McCarthy","year":"2021"},{"key":"10.1016\/j.caeai.2025.100414_br0670","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1080\/08957347.2018.1495216","article-title":"Applying a thurstonian, two-stage method in the standardized assessment of writing","volume":"31","author":"McGrane","year":"2018","journal-title":"Applied Measurement in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0680","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3758\/BF03214410","article-title":"Comparison and choice: Relations between similarity processes and decision processes","volume":"2","author":"Medin","year":"1995","journal-title":"Psychonomic Bulletin & Review"},{"key":"10.1016\/j.caeai.2025.100414_br0690","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics: Student research workshop","first-page":"378","article-title":"Unsupervised learning of discourse-aware text representation for essay scoring","author":"Mim","year":"2019"},{"key":"10.1016\/j.caeai.2025.100414_br0700","doi-asserted-by":"crossref","DOI":"10.1016\/j.rmal.2023.100050","article-title":"Exploring the potential of using an ai language model for automated essay scoring","volume":"2","author":"Mizumoto","year":"2023","journal-title":"Research Methods in Applied Linguistics"},{"key":"10.1016\/j.caeai.2025.100414_br0710","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1111\/ejed.12527","article-title":"Towards hybrid human-ai learning technologies","volume":"57","author":"Molenaar","year":"2022","journal-title":"European Journal of Education"},{"key":"10.1016\/j.caeai.2025.100414_br0720","series-title":"Computer assisted assessment. Research into E-assessment","first-page":"69","article-title":"Comparative judgment within online assessment: Exploring students feedback reactions","author":"Mortier","year":"2015"},{"key":"10.1016\/j.caeai.2025.100414_br0730","doi-asserted-by":"crossref","first-page":"3005","DOI":"10.1007\/s10462-022-10246-w","article-title":"Human-in-the-loop machine learning: A state of the art","volume":"56","author":"Mosqueira-Rey","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.caeai.2025.100414_br0740","first-page":"205","article-title":"Using digital representations of practical production work for summative assessment","volume":"21","author":"Newhouse","year":"2014","journal-title":"Assessment in Education: Principles, Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br0750","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1080\/02602938.2020.1823314","article-title":"The power of internal feedback: Exploiting natural comparison processes","volume":"46","author":"Nicol","year":"2021","journal-title":"Assessment Evaluation Higher Education"},{"author":"Parekh","key":"10.1016\/j.caeai.2025.100414_br0760"},{"key":"10.1016\/j.caeai.2025.100414_br0770","series-title":"Proceedings of the 14th ACM conference on recommender systems","first-page":"388","article-title":"What does bert know about books, movies and music? Probing bert for conversational recommendation","author":"Penha","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br0780","series-title":"Proceedings of the 2015 conference on empirical methods in natural language processing","first-page":"431","article-title":"Flexible domain adaptation for automated essay scoring using correlated linear regression","author":"Phandi","year":"2015"},{"year":"2020","series-title":"Embeddings in natural language processing: Theory and advances in vector representations of meaning","author":"Pilehvar","key":"10.1016\/j.caeai.2025.100414_br0790"},{"key":"10.1016\/j.caeai.2025.100414_br0800","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.compedu.2019.04.009","article-title":"Integrating machine learning into item response theory for addressing the cold start problem in adaptive learning systems","volume":"137","author":"Pliakos","year":"2019","journal-title":"Computers and Education"},{"key":"10.1016\/j.caeai.2025.100414_br0810","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s10798-011-9189-x","article-title":"Comparative judgement for assessment","volume":"22","author":"Pollitt","year":"2012","journal-title":"International Journal of Technology and Design Education"},{"key":"10.1016\/j.caeai.2025.100414_br0820","first-page":"281","article-title":"The method of adaptive comparative judgement. Assessment in education: Principles","volume":"19","author":"Pollitt","year":"2012","journal-title":"Policy & Practice"},{"year":"2012","series-title":"Using adaptive comparative judgement to obtain a highly reliable rank order in summative assessment","author":"Pollitt","key":"10.1016\/j.caeai.2025.100414_br0830"},{"key":"10.1016\/j.caeai.2025.100414_br0840","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.cognition.2017.05.010","article-title":"That certain something! Focusing on similarities reduces judgmental uncertainty","volume":"165","author":"Posten","year":"2017","journal-title":"Cognition"},{"key":"10.1016\/j.caeai.2025.100414_br0850","doi-asserted-by":"crossref","first-page":"89","DOI":"10.20343\/teachlearninqu.5.2.8","article-title":"Compair: A new online tool using adaptive comparative judgement to support learning with peer feedback","volume":"5","author":"Potter","year":"2017","journal-title":"Teaching & Learning Inquiry"},{"key":"10.1016\/j.caeai.2025.100414_br0860","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1007\/s10462-021-10068-2","article-title":"An automated essay scoring systems: A systematic literature review","volume":"55","author":"Ramesh","year":"2022","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.caeai.2025.100414_br0870","series-title":"36th pupils' atitudes towards technology conference","first-page":"378","article-title":"Addressing the issue of bias in the measurement of reliability in the method of adaptive comparative judgment","author":"Rangel-Smith","year":"2018"},{"key":"10.1016\/j.caeai.2025.100414_br0880","series-title":"Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Demonstrations","first-page":"97","article-title":"\u201cwhy should I trust you?\u201c: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.1016\/j.caeai.2025.100414_br0890","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/B978-0-12-387691-1.00007-7","article-title":"The power of comparison in learning and instruction: Learning outcomes supported by different types of comparisons","volume":"55","author":"Rittle-Johnson","year":"2011","journal-title":"Psychology of Learning and Motivation"},{"key":"10.1016\/j.caeai.2025.100414_br0900","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/BF00117714","article-title":"Formative assessment and the design of instructional systems","volume":"18","author":"Sadler","year":"1989","journal-title":"Instructional Science"},{"key":"10.1016\/j.caeai.2025.100414_br0910","series-title":"Assessment: Case studies, experience and practice from higher education","first-page":"130","article-title":"Ah!\u2026 so that's \u2018quality\u2019","author":"Sadler","year":"2014"},{"key":"10.1016\/j.caeai.2025.100414_br0920","series-title":"Proceedings of the 25th annual international ACM SIGIR conference on research and development in information retrieval","first-page":"253","article-title":"Methods and metrics for cold-start recommendations","author":"Schein","year":"2002"},{"key":"10.1016\/j.caeai.2025.100414_br0930","series-title":"Transactions of the association for computational linguistics","first-page":"247","article-title":"Machine learning\u2013driven language assessment","author":"Settles","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br0940","series-title":"Proceedings of COLING 2014, the 25th international conference on computational linguistics: Technical papers","first-page":"950","article-title":"Lexical chaining for measuring discourse coherence quality in test-taker essays","author":"Somasundaran","year":"2014"},{"key":"10.1016\/j.caeai.2025.100414_br0950","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), online","first-page":"6723","article-title":"Multi-stage pre-training for automated Chinese essay scoring","author":"Song","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br0960","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1080\/08957347.2016.1171769","article-title":"Evaluating comparative judgment as an approach to essay scoring","volume":"29","author":"Steedle","year":"2016","journal-title":"Applied Measurement in Education"},{"key":"10.1016\/j.caeai.2025.100414_br0970","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1109\/TCSS.2022.3210406","article-title":"Adapting new learners and new resources to micro open learning via online computation","volume":"9","author":"Sun","year":"2022","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"10.1016\/j.caeai.2025.100414_br0980","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/e24091206","article-title":"Improving automated essay scoring by prompt prediction and matching","volume":"24","author":"Sun","year":"2022","journal-title":"Entropy"},{"key":"10.1016\/j.caeai.2025.100414_br0990","series-title":"Proceedings of the 2016 conference on empirical methods in natural language processing","first-page":"1882","article-title":"A neural approach to automated essay scoring","author":"Taghipour","year":"2016"},{"key":"10.1016\/j.caeai.2025.100414_br1000","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1037\/h0070288","article-title":"A law of comparative judgment","volume":"34","author":"Thurstone","year":"1927","journal-title":"Psychological Review"},{"key":"10.1016\/j.caeai.2025.100414_br1010","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1037\/h0065439","article-title":"The method of paired comparisons for social values","volume":"21","author":"Thurstone","year":"1927","journal-title":"Journal of Abnormal and Social Psychology"},{"key":"10.1016\/j.caeai.2025.100414_br1020","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/s41237-021-00142-y","article-title":"A review of deep-neural automated essay scoring models","volume":"48","author":"Uto","year":"2021","journal-title":"Behaviormetrika"},{"key":"10.1016\/j.caeai.2025.100414_br1030","series-title":"Technology enhanced assessment","first-page":"23","article-title":"Feedback opportunities of comparative judgement: An overview of possible features and acceptance at different user levels","author":"Van Gasse","year":"2017"},{"key":"10.1016\/j.caeai.2025.100414_br1040","series-title":"Advances in neural information processing systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.caeai.2025.100414_br1050","first-page":"541","article-title":"A meta-analysis on the reliability of comparative judgement","volume":"26","author":"Verhavert","year":"2019","journal-title":"Assessment in Education: Principles, Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br1060","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1177\/0146621617748321","article-title":"Scale separation reliability: What does it mean in the context of comparative judgment?","volume":"42","author":"Verhavert","year":"2018","journal-title":"Applied Psychological Measurement"},{"key":"10.1016\/j.caeai.2025.100414_br1070","doi-asserted-by":"crossref","DOI":"10.3389\/feduc.2021.785919","article-title":"The accuracy and efficiency of a reference-based adaptive selection algorithm for comparative judgment","volume":"6","author":"Verhavert","year":"2022","journal-title":"Frontiers in Education"},{"key":"10.1016\/j.caeai.2025.100414_br1080","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"13999","article-title":"Aggregating multiple heuristic signals as supervision for unsupervised automated essay scoring","author":"Wang","year":"2023"},{"key":"10.1016\/j.caeai.2025.100414_br1090","series-title":"Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: Human language technologies","first-page":"3416","article-title":"On the use of bert for automated essay scoring: Joint learning of multi-scale essay representation","author":"Wang","year":"2022"},{"key":"10.1016\/j.caeai.2025.100414_br1100","article-title":"Reducing workload in short answer grading using machine learning","volume":"1\u201327doi","author":"Weegar","year":"2023","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"10.1016\/j.caeai.2025.100414_br1110","first-page":"1","article-title":"A comparative judgement approach to the large-scale assessment of primary writing in England","volume":"27","author":"Wheadon","year":"2019","journal-title":"Assessment in Education: Principles, Policy & Practice"},{"key":"10.1016\/j.caeai.2025.100414_br1120","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s40593-020-00236-w","article-title":"Automated feedback and automated scoring in the elementary grades: Usage, attitudes, and associations with writing outcomes in a districtwide implementation of mi write","volume":"31","author":"Wilson","year":"2021","journal-title":"International Journal of Artificial Intelligence in Education"},{"key":"10.1016\/j.caeai.2025.100414_br1130","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1080\/00461520.2023.2224444","article-title":"Toward a cohesive psychological science of effective feedback","volume":"58","author":"Winstone","year":"2023","journal-title":"Educational Psychologist"},{"key":"10.1016\/j.caeai.2025.100414_br1140","doi-asserted-by":"crossref","first-page":"125403","DOI":"10.1109\/ACCESS.2021.3110683","article-title":"A hierarchical bert-based transfer learning approach for multi-dimensional essay scoring","volume":"9","author":"Xue","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.caeai.2025.100414_br1150","series-title":"Handbook of automated scoring","first-page":"297","article-title":"Validation of automated scoring systems","author":"Yan","year":"2020"},{"key":"10.1016\/j.caeai.2025.100414_br1160","series-title":"Advancing natural language processing in educational assessment","first-page":"15","article-title":"Psychometric considerations when using deep learning for automated scoring","author":"Yaneva","year":"2023"},{"key":"10.1016\/j.caeai.2025.100414_br1170","series-title":"Proceedings of the tenth workshop on innovative use of NLP for building educational applications","first-page":"224","article-title":"Task-independent features for automated essay grading","author":"Zesch","year":"2015"},{"key":"10.1016\/j.caeai.2025.100414_br1180","series-title":"Proceedings of the 16th workshop on innovative use of NLP for building educational applications, online","first-page":"85","article-title":"Essay quality signals as weak supervision for source-based essay scoring","author":"Zhang","year":"2021"}],"container-title":["Computers and Education: Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25000542?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666920X25000542?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T13:57:50Z","timestamp":1765807070000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666920X25000542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":118,"alternative-id":["S2666920X25000542"],"URL":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100414","relation":{},"ISSN":["2666-920X"],"issn-type":[{"type":"print","value":"2666-920X"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Opportunities of natural language processing for comparative judgment assessment of essays","name":"articletitle","label":"Article Title"},{"value":"Computers and Education: Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.caeai.2025.100414","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"100414"}}