{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:53:15Z","timestamp":1785523995199,"version":"3.56.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"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 Data Sci Anal"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s41060-026-01240-4","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:30:46Z","timestamp":1785519046000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From clustering to classification: mining code schemas for accurate identification of student solution strategies"],"prefix":"10.1007","volume":"22","author":[{"given":"Ying","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dayu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cifa","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"issue":"10","key":"1240_CR1","first-page":"131","volume":"2","author":"MA Revilla","year":"2008","unstructured":"Revilla, M.A., Manzoor, S., Liu, R.: Competitive learning in informatics: the uva online judge experience. Olympiads. In. Informatics 2(10), 131\u2013148 (2008)","journal-title":"Olympiads. In. Informatics"},{"issue":"2","key":"1240_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2699751","volume":"22","author":"EL Glassman","year":"2015","unstructured":"Glassman, E.L., Scott, J., Singh, R., Guo, P.J., Miller, R.C.: Overcode: visualizing variation in student solutions to programming problems at scale. ACM Trans. Comput. Hum. Interact. (TOCHI) 22(2), 1\u201335 (2015)","journal-title":"ACM Trans. Comput. Hum. Interact. (TOCHI)"},{"key":"1240_CR3","doi-asserted-by":"crossref","unstructured":"Joyner, D., Arrison, R., Ruksana, M., Salguero, E., Wang, Z., Wellington, B., Yin, K.: From clusters to content: using code clustering for course improvement. In: Proceedings of the 50th ACM Technical Symposium on Computer Science Education, pp. 780\u2013786. (2019)","DOI":"10.1145\/3287324.3287459"},{"key":"1240_CR4","doi-asserted-by":"crossref","unstructured":"Staubitz, T., Klement, H., Renz, J., Teusner, R., and Meinel, C.: Towards practical programming exercises and automated assessment in massive open online courses, In 2015 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE). IEEE, pp. 23\u201330 (2015)","DOI":"10.1109\/TALE.2015.7386010"},{"issue":"4","key":"1240_CR5","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s11858-017-0853-9","volume":"49","author":"K Durkin","year":"2017","unstructured":"Durkin, K., Star, J.R., Rittle-Johnson, B.: Using comparison of multiple strategies in the mathematics classroom: lessons learned and next steps. ZDM 49(4), 585\u2013597 (2017)","journal-title":"ZDM"},{"key":"1240_CR6","doi-asserted-by":"crossref","unstructured":"Luo, L., Zeng, Q.: Solminer: mining distinct solutions in programs. In: Proceedings of the 38th International Conference on Software Engineering Companion, pp. 481\u2013490. (2016)","DOI":"10.1145\/2889160.2889202"},{"issue":"4","key":"1240_CR7","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1080\/10508406.2014.954750","volume":"23","author":"P Blikstein","year":"2014","unstructured":"Blikstein, P., Worsley, M., Piech, C., Sahami, M., Cooper, S., Koller, D.: Programming pluralism: using learning analytics to detect patterns in the learning of computer programming. J. Learn. Sci. 23(4), 561\u2013599 (2014)","journal-title":"J. Learn. Sci."},{"key":"1240_CR8","doi-asserted-by":"crossref","unstructured":"Yin, H., Moghadam, J., Fox, A.: Clustering student programming assignments to multiply instructor leverage. In: Proceedings of the second (2015) ACM conference on learning@ scale, pp. 367\u2013372. (2015)","DOI":"10.1145\/2724660.2728695"},{"key":"1240_CR9","doi-asserted-by":"crossref","unstructured":"Gao, L., Wan, B., Fang, C., Li, Y., Chen, C.: Automatic clustering of different solutions to programming assignments in computing education. In: Proceedings of the ACM Conference on Global Computing Education, pp. 164\u2013170. (2019)","DOI":"10.1145\/3300115.3309515"},{"issue":"4","key":"1240_CR10","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1145\/3296979.3192387","volume":"53","author":"S Gulwani","year":"2018","unstructured":"Gulwani, S., Radi\u010dek, I., Zuleger, F.: Automated clustering and program repair for introductory programming assignments. ACM SIGPLAN Notices 53(4), 465\u2013480 (2018)","journal-title":"ACM SIGPLAN Notices"},{"key":"1240_CR11","doi-asserted-by":"crossref","unstructured":"Artser, E., Birillo, A., Golubev, Y., Tigina, M., Keuning, H., Vyahhi, N., Bryksin, T.: Clustering mooc programming solutions to diversify their presentation to students. In: Proceedings of the 24th Koli Calling International Conference on Computing Education Research, pp. 1\u20138. (2024)","DOI":"10.1145\/3699538.3699548"},{"key":"1240_CR12","doi-asserted-by":"crossref","unstructured":"Orvalho, P., Janota, M., Manquinho, V.: Invaastcluster: on applying invariant-based program clustering to introductory programming assignments, J. Syst. Softw. p. 112481, (2025)","DOI":"10.1016\/j.jss.2025.112481"},{"issue":"7","key":"1240_CR13","doi-asserted-by":"publisher","first-page":"3462","DOI":"10.3390\/app15073462","volume":"15","author":"Z Tang","year":"2025","unstructured":"Tang, Z., Wang, S., Chen, L.: Deep clustering of student code strategies using multi-view code representation (cmvae). Appl. Sci. 15(7), 3462 (2025)","journal-title":"Appl. Sci."},{"issue":"2","key":"1240_CR14","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1007\/s41060-024-00554-5","volume":"20","author":"JC Paiva","year":"2025","unstructured":"Paiva, J.C., Leal, J.P., Figueira, \u00c1.: Clustering source code from automated assessment of programming assignments. Int. J. Data Sci. Anal. 20(2), 1581\u20131592 (2025)","journal-title":"Int. J. Data Sci. Anal."},{"key":"1240_CR15","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al.: Codebert: a pre-trained model for programming and natural languages, arXiv preprint arXiv:2002.08155, (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"1240_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104866","volume":"138","author":"BA Hassan","year":"2021","unstructured":"Hassan, B.A., Rashid, T.A., Hamarashid, H.K.: A novel cluster detection of covid-19 patients and medical disease conditions using improved evolutionary clustering algorithm star. Comput. Biol. Med. 138, 104866 (2021)","journal-title":"Comput. Biol. Med."},{"issue":"17","key":"1240_CR17","doi-asserted-by":"publisher","first-page":"10987","DOI":"10.1007\/s00521-020-05649-1","volume":"33","author":"BA Hassan","year":"2021","unstructured":"Hassan, B.A., Rashid, T.A.: A multidisciplinary ensemble algorithm for clustering heterogeneous datasets. Neural Comput. Appl. 33(17), 10987\u201311010 (2021)","journal-title":"Neural Comput. Appl."},{"key":"1240_CR18","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.compedu.2018.07.004","volume":"126","author":"T-C Hsu","year":"2018","unstructured":"Hsu, T.-C., Chang, S.-C., Hung, Y.-T.: How to learn and how to teach computational thinking: Suggestions based on a review of the literature. Comput. Edu. 126, 296\u2013310 (2018)","journal-title":"Comput. Edu."},{"issue":"2","key":"1240_CR19","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1111\/jcal.12498","volume":"37","author":"M Kallia","year":"2021","unstructured":"Kallia, M., Sentance, S.: Threshold concepts, conceptions and skills: teachers\u2019 experiences with students\u2019 engagement in functions. J. Comput. Assist. Learn. 37(2), 411\u2013428 (2021)","journal-title":"J. Comput. Assist. Learn."},{"key":"1240_CR20","doi-asserted-by":"crossref","unstructured":"Haldeman, G., Robbins Bernal, J., Wydra, A., Denny, P.: Teaching program decomposition in cs1: a conceptual framework for improved code quality. In: Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1, pp. 443\u2013449. (2025)","DOI":"10.1145\/3641554.3701880"},{"issue":"5","key":"1240_CR21","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1145\/2902362","volume":"59","author":"A Hindle","year":"2016","unstructured":"Hindle, A., Barr, E.T., Gabel, M., Su, Z., Devanbu, P.: On the naturalness of software. Commun. ACM 59(5), 122\u2013131 (2016)","journal-title":"Commun. ACM"},{"issue":"7","key":"1240_CR22","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1109\/TSE.2002.1019480","volume":"28","author":"T Kamiya","year":"2002","unstructured":"Kamiya, T., Kusumoto, S., Inoue, K.: Ccfinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans. Softw. Eng. 28(7), 654\u2013670 (2002)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"1240_CR23","unstructured":"Allamanis, M., Peng, H., Sutton, C.: A convolutional attention network for extreme summarization of source code. In: International conference on machine learning. PMLR, pp. 2091\u20132100. (2016)"},{"key":"1240_CR24","doi-asserted-by":"crossref","unstructured":"Mou, L., Li, G., Zhang, L., Wang, T., Jin, Z.: Convolutional neural networks over tree structures for programming language processing, In: Proceedings of the AAAI conference on artificial intelligence30 (1) (2016)","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"1240_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, X., Zhang, H., Sun, H., Wang, K., Liu, X.: A novel neural source code representation based on abstract syntax tree, In: 2019 IEEE\/ACM 41st International Conference on Software Engineering (ICSE). IEEE, pp. 783\u2013794 (2019)","DOI":"10.1109\/ICSE.2019.00086"},{"key":"1240_CR26","unstructured":"Allamanis, M., Brockschmidt, M., Khademi, M.: Learning to represent programs with graphs, arXiv preprint arXiv:1711.00740 (2017)"},{"key":"1240_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wang, W., Zhang, H., Li, G., Jin, Z.: Learning to represent programs with heterogeneous graphs, In: Proceedings of the 30th IEEE\/ACM international conference on program comprehension, pp. 378\u2013389 (2022)","DOI":"10.1145\/3524610.3527905"},{"key":"1240_CR28","unstructured":"Hellendoorn, V.J., Sutton, C., Singh, R., Maniatis, P., Bieber, D.: Global relational models of source code. In: International conference on learning representations, (2019)"},{"key":"1240_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3290353","volume":"3","author":"U Alon","year":"2019","unstructured":"Alon, U., Zilberstein, M., Levy, O., Yahav, E.: code2vec: learning distributed representations of code. Proc. ACM Progr. Lang. 3, 1\u201329 (2019)","journal-title":"Proc. ACM Progr. Lang."},{"key":"1240_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need, advances in neural information processing systems, 30, (2017)"},{"key":"1240_CR31","unstructured":"Guo, D., Ren, S., Lu, S., Feng, Z., Tang, D., Liu, S., Zhou, L., Duan, N., Svyatkovskiy, A., Fu, S.: Graphcodebert: Pre-training code representations with data flow, arXiv preprint arXiv:2009.08366 (2020)"},{"key":"1240_CR32","unstructured":"Jiang, X., Zheng, Z., Lyu, C., Li, L., Lyu, L.: Treebert: A tree-based pre-trained model for programming language, In: Uncertainty in Artificial Intelligence. PMLR, pp. 54\u201363 (2021)"},{"issue":"3","key":"1240_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3636430","volume":"18","author":"S Tipirneni","year":"2024","unstructured":"Tipirneni, S., Zhu, M., Reddy, C.K.: Structcoder: structure-aware transformer for code generation. ACM Trans. Knowl. Discov. Data 18(3), 1\u201320 (2024)","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"1240_CR34","doi-asserted-by":"crossref","unstructured":"Ding, Y., Steenhoek, B., Pei, K., Kaiser, G., Le, W., Ray, B.: Traced: Execution-aware pre-training for source code. In: Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering, pp. 1\u201312. (2024)","DOI":"10.1145\/3597503.3608140"},{"key":"1240_CR35","doi-asserted-by":"crossref","unstructured":"Ahmad, W.U., Chakraborty, S., Ray, B., Chang, K.-W.: Unified pre-training for program understanding and generation, arXiv preprint arXiv:2103.06333 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"1240_CR36","unstructured":"Gong, L., Elhoushi, M., Cheung, A.: Ast-t5: Structure-aware pretraining for code generation and understanding, arXiv preprint arXiv:2401.03003 (2024)"},{"key":"1240_CR37","unstructured":"Huang, J., Piech, C., Nguyen, A., Guibas, L.: Syntactic and functional variability of a million code submissions in a machine learning mooc. In: AIED 2013 Workshops Proceedings Volume, vol. 25, (2013)"},{"key":"1240_CR38","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Piech, C., Huang, J., Guibas, L.: Codewebs: scalable homework search for massive open online programming courses. In: Proceedings of the 23rd international conference on World wide web, pp. 491\u2013502. (2014)","DOI":"10.1145\/2566486.2568023"},{"key":"1240_CR39","doi-asserted-by":"crossref","unstructured":"Perry, D.M., Kim, D., Samanta, R., Zhang, X.: Semcluster: clustering of imperative programming assignments based on quantitative semantic features. In: Proceedings of the 40th acm sigplan conference on programming language design and implementation, pp. 860\u2013873. (2019)","DOI":"10.1145\/3314221.3314629"},{"key":"1240_CR40","doi-asserted-by":"crossref","unstructured":"Fu, Y., Osei-Owusu, J., Astorga, A., Zhao, Z.N., Zhang, W., Xie, T.: Pacon: A symbolic analysis approach for tactic-oriented clustering of programming submissions. In: Proceedings of the 2021 ACM SIGPLAN International Symposium on SPLASH-E, pp. 32\u201342. (2021)","DOI":"10.1145\/3484272.3484963"},{"key":"1240_CR41","unstructured":"Alon, U., Brody, S., Levy, O., Yahav, E.: code2seq: Generating sequences from structured representations of code, arXiv preprint arXiv:1808.01400 (2018)"},{"key":"1240_CR42","doi-asserted-by":"crossref","unstructured":"Effenberger, T., Pel\u00e1nek, R.: Interpretable clustering of students\u2019 solutions in introductory programming. In: International Conference on Artificial Intelligence in Education, pp. 101\u2013112. Springer (2021)","DOI":"10.1007\/978-3-030-78292-4_9"},{"key":"1240_CR43","doi-asserted-by":"crossref","unstructured":"Hu, Y., Zou, D., Peng, J., Wu, Y., Shan, J., Jin, H.: Treecen: Building tree graph for scalable semantic code clone detection. In: Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering, pp. 1\u201312. (2022)","DOI":"10.1145\/3551349.3556927"},{"key":"1240_CR44","doi-asserted-by":"crossref","unstructured":"Mathew, G., Parnin, C., Stolee, K.T.: Slacc: Simion-based language agnostic code clones. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering, pp. 210\u2013221. (2020)","DOI":"10.1145\/3377811.3380407"},{"key":"1240_CR45","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification, arXiv preprint arXiv:1408.5882 (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"1240_CR46","doi-asserted-by":"crossref","unstructured":"Graves, A. Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional lstm networks for improved phoneme classification and recognition, In: International conference on artificial neural networks. Springer, pp. 799\u2013804 (2005)","DOI":"10.1007\/11550907_126"},{"key":"1240_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, P., Shi, W., Tian, J., Qi, Z., Li, B., Hao, H., Xu, B.: Attention-based bidirectional long short-term memory networks for relation classification, In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers), pp. 207\u2013212 (2016)","DOI":"10.18653\/v1\/P16-2034"},{"key":"1240_CR48","unstructured":"Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., Zhang, L., Liu, T., Zhang, J., Yu, B., Lu, K., et al.: Qwen2. 5-coder technical report, arXiv preprint arXiv:2409.12186, (2024)"},{"issue":"2","key":"1240_CR49","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in pcm. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"1\u20132","key":"1240_CR50","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Log. Quar. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Log. Quar."},{"key":"1240_CR51","doi-asserted-by":"crossref","unstructured":"Sch\u00fctze, H., Manning, C.D., Raghavan, P.: Introduction to information retrieval, vol. 39, Cambridge University Press Cambridge (2008)","DOI":"10.1017\/CBO9780511809071"},{"key":"1240_CR52","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987)","journal-title":"J. Comput. Appl. Math."}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01240-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-026-01240-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01240-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:30:57Z","timestamp":1785519057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-026-01240-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["1240"],"URL":"https:\/\/doi.org\/10.1007\/s41060-026-01240-4","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"assertion":[{"value":"14 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"250"}}