{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:47:30Z","timestamp":1787924850246,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,3]]},"DOI":"10.1145\/3706468.3706523","type":"proceedings-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T09:04:11Z","timestamp":1740128651000},"page":"439-450","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6860-4404","authenticated-orcid":false,"given":"Mohammad","family":"Khalil","sequence":"first","affiliation":[{"name":"Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-2198","authenticated-orcid":false,"given":"Farhad","family":"Vadiee","sequence":"additional","affiliation":[{"name":"Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7148-4028","authenticated-orcid":false,"given":"Ronas","family":"Shakya","sequence":"additional","affiliation":[{"name":"Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4973-0901","authenticated-orcid":false,"given":"Qinyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Mahed Abroshan Andrew Elliott and Mahdi Khalili. 2024. Imposing fairness constraints in synthetic data generation. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics 238 (2024) 2269\u20132277. https:\/\/proceedings.mlr.press\/v238\/abroshan24a.html"},{"key":"e_1_3_3_2_3_2","unstructured":"Ahmed Alaa Boris Van\u00a0Breugel Evgeny Saveliev and Mihaela Van Der\u00a0Schaar. 2022. How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models. Proceedings of the 39 th International Conference on Machine Learning Baltimore Maryland USA PMLR 162 2022 (2022). https:\/\/proceedings.mlr.press\/v162\/alaa22a\/alaa22a.pdf"},{"key":"e_1_3_3_2_4_2","unstructured":"Chris Alexiuk Shashank Verma and Vivienne Zhang. 2024. Leverage the Latest Open Models for Synthetic Data Generation with NVIDIA Nemotron-4 340B. https:\/\/developer.nvidia.com\/blog\/leverage-our-latest-open-models-for-synthetic-data-generation-with-nvidia-nemotron-4-340b\/"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Francis Anscombe. 1973. Graphs in Statistical Analysis. The American Statistician 27 (1973) 17\u201321. 10.2307\/2682899","DOI":"10.2307\/2682899"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Alan\u00a0M. Berg Stefan\u00a0T. Mol G\u00e1bor Kismih\u00f3k and Niall Sclater. 2016. The role of a reference synthetic data generator within the field of learning analytics. Journal of Learning Analytics 3 (2016) 107\u2013128. 10.18608\/jla.2016.31.7","DOI":"10.18608\/jla.2016.31.7"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Anabel Bethencourt-Aguilar Dagoberto Castellanos-Nieves Juan\u00a0Jos\u00e9 Sosa-Alonso and Manuel Area-Moreira. 2023. Use of Generative Adversarial Networks (GANs) in Educational Technology Research. Journal of New Approaches in Educational Research 12 (2023) 153\u2013153. 10.7821\/naer.2023.1.1231","DOI":"10.7821\/naer.2023.1.1231"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Karan Bhanot Miao Qi John\u00a0S Erickson Isabelle Guyon and Kristin\u00a0P Bennett. 2021. The Problem of Fairness in Synthetic Healthcare Data. Entropy 23 (2021). 10.3390\/e23091165","DOI":"10.3390\/e23091165"},{"key":"e_1_3_3_2_9_2","unstructured":"Vadim Borisov Kathrin Sessler Tobias Leemann Martin Pawelczyk and Gjergji Kasneci. 2023. Language Models are Realistic Tabular Data Generators. ArXiv.org (2023). https:\/\/arxiv.org\/pdf\/2210.06280"},{"key":"e_1_3_3_2_10_2","unstructured":"Boris\u00a0van Breugel and Mihaela van\u00a0der Schaar. 2022. Why Tabular Foundation Models Should Be a Research Priority. Arxiv.org (2022). https:\/\/arxiv.org\/html\/2405.01147v1#S7"},{"key":"e_1_3_3_2_11_2","unstructured":"S\u00e9bastien Bubeck Varun Chandrasekaran Ronen Eldan John\u00a0A Gehrke Eric Horvitz Ece Kamar Peter Lee Yin\u00a0Tat Lee Yuan-Fang Li Scott\u00a0M Lundberg Harsha Nori Hamid Palangi Marco\u00a0Tulio Ribeiro and Yi Zhang. 2023. Sparks of artificial general intelligence: Early experiments with GPT-4. ArXiv abs\/2303.12712 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257663729"},{"key":"e_1_3_3_2_12_2","unstructured":"Paulo Cortez. 2014. UCI Machine Learning Repository. https:\/\/archive.ics.uci.edu\/dataset\/320\/student+performance"},{"key":"e_1_3_3_2_13_2","unstructured":"Tukur Dahiru. 2008. P - value a true test of statistical significance? A cautionary note. Annals of Ibadan postgraduate medicine 6 (2008) 21\u20136. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC4111019\/"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Shane Dawson Srecko Joksimovic Oleksandra Poquet and George Siemens. 2019. Increasing the impact of learning analytics. LAK19: Proceedings of the 9th International Conference on Learning Analytics & Knowledge (2019) 446\u2013455. 10.1145\/3303772.3303784","DOI":"10.1145\/3303772.3303784"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Erica Espinosa and Alvaro Figueira. 2023. On the Quality of Synthetic Generated Tabular Data. Mathematics 11 (2023). 10.3390\/math11153278","DOI":"10.3390\/math11153278"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Wenzheng Feng Jie Tang and Tracy\u00a0Xiao Liu. 2019. Understanding dropouts in MOOCs. AAAI\u201919\/IAAI\u201919\/EAAI\u201919: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence (2019). 10.1609\/aaai.v33i01.3301517","DOI":"10.1609\/aaai.v33i01.3301517"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Rebecca Ferguson and Doug Clow. 2017. Where is the evidence? a call to action for learning analytics. LAK \u201917: Proceedings of the Seventh International Learning Analytics & Knowledge Conference (2017) 56\u201365. 10.1145\/3027385.3027396","DOI":"10.1145\/3027385.3027396"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Alvaro Figueira and Bruno Vaz. 2022. Survey on Synthetic Data Generation Evaluation Methods and GANs. Mathematics 10 (2022) 2733. 10.3390\/math10152733","DOI":"10.3390\/math10152733"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Brendan Flanagan Rwitajit Majumdar and Hiroaki Ogata. 2022. Fine Grain Synthetic Educational Data: Challenges and Limitations of Collaborative Learning Analytics. IEEE Access 10 (2022) 26230\u201326241. 10.1109\/access.2022.3156073","DOI":"10.1109\/access.2022.3156073"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Mikel Hernadez Gorka Epelde Ane Alberdi Rodrigo Cilla and Debbie Rankin. 2023. Synthetic Tabular Data Evaluation in the Health Domain Covering Resemblance Utility and Privacy Dimensions. Methods of Information in Medicine 62 (2023) e19\u2013e38. 10.1055\/s-0042-1760247","DOI":"10.1055\/s-0042-1760247"},{"key":"e_1_3_3_2_21_2","unstructured":"Geoffrey Hinton and Sam Roweis. 2002. Stochastic Neighbor Embedding. https:\/\/cs.nyu.edu\/\u00a0roweis\/papers\/sne_final.pdf"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Markus Hittmeir Andreas Ekelhart and Rudolf Mayer. 2019. On the utility of synthetic data: An empirical evaluation on machine learning tasks. ARES \u201919: Proceedings of the 14th International Conference on Availability Reliability and Security (2019). 10.1145\/3339252.3339281","DOI":"10.1145\/3339252.3339281"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Lan Jiang Clara Belitz and Nigel Bosch. 2024. Synthetic dataset generation for fairer unfairness research. LAK \u201924: Proceedings of the 14th Learning Analytics and Knowledge Conference (2024) 200\u2013209. 10.1145\/3636555.3636868","DOI":"10.1145\/3636555.3636868"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"James Jordon Lukasz Szpruch Florimond Houssiau Mirko Bottarelli Giovanni Cherubin Carsten Maple Samuel\u00a0N Cohen and Adrian Weller. 2022. Synthetic Data \u2013 what why and how? The Royal Society (2022). 10.48550\/arxiv.2205.03257","DOI":"10.48550\/arxiv.2205.03257"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2020. Analyzing and Improving the Image Quality of StyleGAN. 8110\u20138119\u00a0pages. https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Karras_Analyzing_and_Improving_the_Image_Quality_of_StyleGAN_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Mohammad Khalil. 2018. Learning Analytics in Massive Open Online Courses. ArXiv.org (2018). 10.48550\/arXiv.1802.09344","DOI":"10.48550\/arXiv.1802.09344"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Harsh Kumar Ilya Musabirov Joseph\u00a0Jay Williams and Michael Liut. 2023. QuickTA: Exploring the Design Space of Using Large Language Models to Provide Support to Students. Learning Analytics and Knowledge Conference (LAK\u201923) (2023). https:\/\/tspace.library.utoronto.ca\/bitstream\/1807\/127196\/1\/2023_Kumar_QuickTA_exploring_design_space.pdf","DOI":"10.1145\/3544549.3585614"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Jakub Kuzilek Martin Hlosta and Zdenek Zdrahal. 2017. Open University Learning Analytics dataset. Scientific Data 4 (2017) 170171. 10.1038\/sdata.2017.171","DOI":"10.1038\/sdata.2017.171"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Jiayin Lin Geng Sun Jun Shen Tingru Cui Ping Yu Dongming Xu Li Li and Ghassan Beydoun. 2019. Towards the readiness of learning analytics data for micro learning. Services Computing \u2013 SCC 2019: 16th International Conference Held as Part of the Services Conference Federation SCF 2019 San Diego CA USA June 25\u201330 2019 Proceedings (2019) 66\u201376. 10.1007\/978-3-030-23554-3_5","DOI":"10.1007\/978-3-030-23554-3_5"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Qinyi Liu Oscar Deho Farhad Vadiee Mohammad Khalil Srecko Joksimovic and George Siemens. 2025. Can Synthetic Data Be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms. In Proceedings of the 15th International Learning Analytics and Knowledge Conference (LAK\u201925). ACM. (2025). 10.1145\/3706468.3706546","DOI":"10.1145\/3706468.3706546"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Qinyi Liu and Mohammad Khalil. 2023. Understanding privacy and data protection issues in learning analytics using a systematic review. British Journal of Educational Technology 54 (2023). 10.1111\/bjet.13388","DOI":"10.1111\/bjet.13388"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Qinyi Liu Mohammad Khalil Jelena Jovanovic and Ronas Shakya. 2024. Scaling while privacy preserving: A comprehensive synthetic tabular data generation and evaluation in learning analytics. LAK \u201924: Proceedings of the 14th Learning Analytics and Knowledge Conference (2024) 620\u2013631. 10.1145\/3636555.3636921","DOI":"10.1145\/3636555.3636921"},{"key":"e_1_3_3_2_33_2","unstructured":"Ruibo Liu Jerry Wei Fangyu Liu Google Deepmind Chenglei Si Yanzhe Zhang Jinmeng Rao Steven Zheng Daiyi Peng Diyi Yang Denny Zhou and Andrew Dai. 2024. Best Practices and Lessons Learned on Synthetic Data. Arxiv.org (2024). https:\/\/arxiv.org\/pdf\/2404.07503"},{"key":"e_1_3_3_2_34_2","unstructured":"Tennison Liu Zhaozhi Qian Jeroen Berrevoets and van. 2023. GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure. https:\/\/openreview.net\/forum?id=fPVRcJqspu"},{"key":"e_1_3_3_2_35_2","unstructured":"Laurens van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE Laurens van der Maaten. Journal of Machine Learning Research 9 (2008) 2579\u20132605. https:\/\/www.jmlr.org\/papers\/volume9\/vandermaaten08a\/vandermaaten08a.pdf"},{"key":"e_1_3_3_2_36_2","first-page":"91","volume-title":"18th International Conference on Machine Learning and Data Mining (MLDM-22). New York, US: IBAI Publishing","author":"Mendikowski Melle","year":"2022","unstructured":"Melle Mendikowski and Mattis Hartwig. 2022. Creating customers that never existed: Synthesis of e-commerce data using CTGAN. In 18th International Conference on Machine Learning and Data Mining (MLDM-22). New York, US: IBAI Publishing. 91\u2013105."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"M.L. Men\u00e9ndez J.A. Pardo L. Pardo and M.C. Pardo. 1997. The Jensen-Shannon divergence. Journal of the Franklin Institute 334 (1997) 307\u2013318. 10.1016\/s0016-0032(96)00063-4","DOI":"10.1016\/s0016-0032(96)00063-4"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Marko Miletic and Murat Sariyar. 2024. Assessing the Potentials of LLMs and GANs as StateoftheArt Tabular Synthetic Data Generation Methods. Privacy in Statistical Databases (2024) 374\u2013389. 10.3390\/app14145975","DOI":"10.3390\/app14145975"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Luis Moles Alain Andres Goretti Echegaray and Fernando Boto. 2024. Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets. Mathematics 12 (2024). 10.3390\/math12121898","DOI":"10.3390\/math12121898"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Abdallah Moubayed MohammadNoor Injadat Abdallah Shami Ali\u00a0Bou Nassif and Hanan Lutfiyya. 2020. Student Performance and Engagement Prediction in eLearning datasets. IEEE dataport (2020). 10.21227\/4xkr-0f88","DOI":"10.21227\/4xkr-0f88"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Victor\u00a0M. Panaretos and Yoav Zemel. 2019. Statistical Aspects of Wasserstein Distances. Annual Review of Statistics and Its Application 6 (2019) 405\u2013431. 10.1146\/annurev-statistics-030718-104938","DOI":"10.1146\/annurev-statistics-030718-104938"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Stanislav Pozdniakov Jonathan Brazil Solmaz Abdi Aneesha Bakharia Shazia Sadiq Dragan Ga\u0161evi\u0107 Paul Denny and Hassan Khosravi. 2024. Large language models meet user interfaces: The case of provisioning feedback. Computers and Education: Artificial Intelligence 7 (2024) 100289. 10.1016\/j.caeai.2024.100289","DOI":"10.1016\/j.caeai.2024.100289"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Paul Prinsloo Mohammad Khalil and Sharon Slade. 2023. Learning analytics as data ecology: a tentative proposal. Journal of Computing in Higher Education 36 (2023). 10.1007\/s12528-023-09355-4","DOI":"10.1007\/s12528-023-09355-4"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Paul Prinsloo Sharon Slade and Mohammad Khalil. 2019. Student data privacy in MOOCs: A sentiment analysis. Distance Education 40 3 (2019) 395\u2013413.","DOI":"10.1080\/01587919.2019.1632171"},{"key":"e_1_3_3_2_45_2","unstructured":"Zhaozhi Qian Bogdan-Constantin Cebere and Mihaela van\u00a0der Schaar. 2023. Synthcity: facilitating innovative use cases of synthetic data in different data modalities. arXiv:https:\/\/arXiv.org\/abs\/2301.07573 [cs] (2023). https:\/\/arxiv.org\/abs\/2301.07573"},{"key":"e_1_3_3_2_46_2","unstructured":"Zhaozhi Qian Rob Davis and Mihaela Van Der\u00a0Schaar. 2024. Synthcity: a benchmark framework for diverse use cases of tabular synthetic data. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/09723c9f291f6056fd1885081859c186-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_3_2_47_2","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). https:\/\/huggingface.co\/openai-community\/gpt2"},{"key":"e_1_3_3_2_48_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. https:\/\/arxiv.org\/pdf\/1910.01108"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Neil Selwyn. 2020. Re-imagining \u2018Learning Analytics\u2019 \u2026 a case for starting again? The Internet and Higher Education 46 (2020) 100745. 10.1016\/j.iheduc.2020.100745","DOI":"10.1016\/j.iheduc.2020.100745"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Wannapon Suraworachet Jennifer Seon and Mutlu Cukurova. 2024. Predicting challenge moments from students\u2019 discourse: A comparison of GPT-4 to two traditional natural language processing approaches. LAK \u201924: Proceedings of the 14th Learning Analytics and Knowledge Conference (2024) 473\u2013485. 10.1145\/3636555.3636905","DOI":"10.1145\/3636555.3636905"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Dimitrios Tzimas and Stavros Demetriadis. 2021. Ethical issues in learning analytics: a review of the field. Educational Technology Research and Development 69 (2021). 10.1007\/s11423-021-09977-4","DOI":"10.1007\/s11423-021-09977-4"},{"key":"e_1_3_3_2_52_2","unstructured":"Kurt VanLehn Stellan Ohlsson and Rod Nason. 1994. Applications of simulated students: An exploration. Journal of artificial intelligence in education 5 (1994) 135\u2013135."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","unstructured":"Deborah West Ann Luzeckyj Bill Searle Danny Toohey Jessica Vanderlelie and Kevin\u00a0R Bell. 2020. Perspectives from the stakeholder: Students\u2019 views regarding learning analytics and data collection. Australasian Journal of Educational Technology 36 6 (2020) 72\u201388. 10.14742\/ajet.5957","DOI":"10.14742\/ajet.5957"},{"key":"e_1_3_3_2_54_2","unstructured":"Lei Xu Maria Skoularidou Alfredo Cuesta-Infante and Kalyan Veeramachaneni. 2019. Modeling Tabular data using Conditional GAN. Neural Information Processing Systems 32 (2019). https:\/\/papers.nips.cc\/paper_files\/paper\/2019\/hash\/254ed7d2de3b23ab10936522dd547b78-Abstract.html"},{"key":"e_1_3_3_2_55_2","unstructured":"Shengzhe Xu Virginia Tech Cho-Ting Lee Mandar Sharma Raquib Yousuf Nikhil Muralidhar and Naren Ramakrishnan. 2024. Are LLMs Naturally Good at Synthetic Tabular Data Generation? ArXiv.org (2024). https:\/\/arxiv.org\/pdf\/2406.14541"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"Lixiang Yan Linxuan Zhao Dragan Gasevic and Roberto Martinez-Maldonado. 2022. Scalability sustainability and ethicality of multimodal learning analytics. LAK22: 12th International Learning Analytics and Knowledge Conference (2022) 13\u201323. 10.1145\/3506860.3506862","DOI":"10.1145\/3506860.3506862"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Chen Zhan Oscar\u00a0Blessed Deho Xuwei Zhang Srecko Joksimovic and Maarten\u00a0de Laat. 2023. Synthetic data generator for student data serving learning analytics: A comparative study. Learning Letters 1 (2023) 5. 10.59453\/KHZW9006","DOI":"10.59453\/KHZW9006"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Yizhe Zhang Siqi Sun Michel Galley Yen-Chun Chen Chris Brockett Xiang Gao Jianfeng Gao Jingjing Liu and Bill Dolan. 2019. DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation. ArXiv.org (2019). https:\/\/arxiv.org\/abs\/1911.00536","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"e_1_3_3_2_59_2","unstructured":"Zilong Zhao Aditya Kunar Robert Birke Lydia Chen and Hiek Van\u00a0der Scheer. 2021. CTAB-GAN: Effective Table Data Synthesizing. Proceedings of Machine Learning Research 157 (2021). https:\/\/proceedings.mlr.press\/v157\/zhao21a\/zhao21a.pdf"}],"event":{"name":"LAK '25: The 15th International Learning Analytics and Knowledge Conference","location":"Dublin Ireland","acronym":"LAK 2025"},"container-title":["Proceedings of the 15th International Learning Analytics and Knowledge Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706468.3706523","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706468.3706523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:56:50Z","timestamp":1750283810000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706468.3706523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":58,"alternative-id":["10.1145\/3706468.3706523","10.1145\/3706468"],"URL":"https:\/\/doi.org\/10.1145\/3706468.3706523","relation":{},"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"2025-03-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}