{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T12:03:37Z","timestamp":1769774617603,"version":"3.49.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032159830","type":"print"},{"value":"9783032159847","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-15984-7_1","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:33:40Z","timestamp":1769718820000},"page":"3-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hardness Sampling: Exploring Instance Hardness in\u00a0Pool-Based Active Learning"],"prefix":"10.1007","author":[{"given":"Gabriel","family":"da S. C. Nogueira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davi","family":"P. dos Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"C. P. L F. de Carvalho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu\u00eds","family":"P. F. Garcia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"1_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-030-61380-8_33","volume-title":"Intelligent Systems","author":"JLM Arruda","year":"2020","unstructured":"Arruda, J.L.M., Prud\u00eancio, R.B.C., Lorena, A.C.: Measuring instance hardness using data complexity measures. In: Cerri, R., Prati, R.C. (eds.) BRACIS 2020. LNCS (LNAI), vol. 12320, pp. 483\u2013497. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61380-8_33"},{"issue":"4","key":"1_CR2","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/coli.07-034-R2","volume":"34","author":"R Artstein","year":"2008","unstructured":"Artstein, R., Poesio, M.: Inter-coder agreement for computational linguistics. Comput. Linguist. 34(4), 555\u2013596 (2008). https:\/\/doi.org\/10.1162\/coli.07-034-R2","journal-title":"Comput. Linguist."},{"issue":"1","key":"1_CR3","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37\u201346 (1960). https:\/\/doi.org\/10.1177\/001316446002000104","journal-title":"Educ. Psychol. Measur."},{"issue":"3","key":"1_CR4","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273\u2013297 (1995). https:\/\/doi.org\/10.1007\/BF00994018","journal-title":"Mach. Learn."},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Culver, M., Kun, D., Scott, S.: Active learning to maximize area under the roc curve. In: Sixth International Conference on Data Mining (ICDM\u201906), pp. 149\u2013158 (2006) https:\/\/doi.org\/10.1109\/ICDM.2006.12","DOI":"10.1109\/ICDM.2006.12"},{"issue":"11","key":"1_CR6","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1007\/s10822-014-9759-6","volume":"28","author":"P Czodrowski","year":"2014","unstructured":"Czodrowski, P.: Count on kappa. J. Comput. Aided Mol. Des. 28(11), 1049\u20131055 (2014). https:\/\/doi.org\/10.1007\/s10822-014-9759-6","journal-title":"J. Comput. Aided Mol. Des."},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Danka, T., Horvath, P.: modAL: a modular active learning framework for Python. arXiv (2018). https:\/\/doi.org\/10.48550\/arXiv.1805.00979","DOI":"10.48550\/arXiv.1805.00979"},{"issue":"1","key":"1_CR8","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(1), 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Dos\u00a0Santos, D.P., de\u00a0Carvalho, A.C.: Selectively inhibiting learning bias for active sampling. In: 2015 Brazilian Conference on Intelligent Systems (BRACIS), pp. 62\u201367 (2015) https:\/\/doi.org\/10.1109\/BRACIS.2015.17","DOI":"10.1109\/BRACIS.2015.17"},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Ebert, S., Fritz, M., Schiele, B.: RALF: a reinforced active learning formulation for object class recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3626\u20133633 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248108","DOI":"10.1109\/CVPR.2012.6248108"},{"key":"1_CR11","first-page":"573","volume":"24","author":"A Fujii","year":"1998","unstructured":"Fujii, A., Inui, K., Tokunaga, T., Tanaka, H.: Selective sampling for example-based word sense disambiguation. Comput. Linguist. 24, 573\u2013597 (1998)","journal-title":"Comput. Linguist."},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrics 27(4), 857\u2013871 (1971). http:\/\/www.jstor.org\/stable\/2528823","DOI":"10.2307\/2528823"},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Hsu, W.N., Lin, H.T.: Active Learning by Learning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, vol.\u00a029, pp. 2659\u20132665 (2015) https:\/\/doi.org\/10.1609\/aaai.v29i1.9597","DOI":"10.1609\/aaai.v29i1.9597"},{"issue":"10","key":"1_CR14","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/TPAMI.2014.2307881","volume":"36","author":"SJ Huang","year":"2014","unstructured":"Huang, S.J., Jin, R., Zhou, Z.H.: Active learning by querying informative and representative examples. IEEE Trans. Pattern Anal. Mach. Intell. 36(10), 1936\u20131949 (2014). https:\/\/doi.org\/10.1109\/TPAMI.2014.2307881","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"1_CR15","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1080\/03610928008827904","volume":"9","author":"RL Iman","year":"1980","unstructured":"Iman, R.L., Davenport, J.M.: Approximations of the critical region of the friedman statistic. Commun. Stat.-Theory Methods 9(6), 571\u2013595 (1980)","journal-title":"Commun. Stat.-Theory Methods"},{"key":"1_CR16","unstructured":"Kelly, M., Longjohn, R., Nottingham, K.: The UCI Machine Learning Repository (2023). https:\/\/archive.ics.uci.edu. Accessed 05 Sept 2024"},{"key":"1_CR17","doi-asserted-by":"publisher","unstructured":"Lancho, C., C.\u00a0P.\u00a0de Souto, M., Lorena, A.C., Mart\u00edn\u00a0de Diego, I.: Complexity-driven sampling for bagging. In: Intelligent Data Engineering and Automated Learning (IDEAL 2023), pp. 15\u201321 (2023). https:\/\/doi.org\/10.1007\/978-3-031-48232-8_2","DOI":"10.1007\/978-3-031-48232-8_2"},{"key":"1_CR18","doi-asserted-by":"publisher","unstructured":"Lewis, D.D., Gale, W.A.: A sequential algorithm for training text classifiers. In: Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, pp. 3\u201312 (1994). https:\/\/doi.org\/10.1007\/978-1-4471-2099-5_1","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Li, X., Guo, Y.: Adaptive active learning for image classification. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 859\u2013866 (2013). https:\/\/doi.org\/10.1109\/CVPR.2013.116","DOI":"10.1109\/CVPR.2013.116"},{"key":"1_CR20","doi-asserted-by":"publisher","unstructured":"Lorena, A.C., Garcia, L.P.F., Lehmann, J., Souto, M.C.P., Ho, T.K.: How complex is your classification problem? a survey on measuring classification complexity. ACM Comput. Surv. 52(5), 107:1\u2013107:34 (2019). https:\/\/doi.org\/10.1145\/3347711","DOI":"10.1145\/3347711"},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Lorena, A.C., Paiva, P.Y.A., Prud\u00eancio, R.B.C.: Trusting my predictions: on the value of instance-level analysis. ACM Comput. Surv. 56(7), 167:1\u2013167:28 (2024). https:\/\/doi.org\/10.1145\/3615354","DOI":"10.1145\/3615354"},{"key":"1_CR22","doi-asserted-by":"publisher","unstructured":"Lu, P.Y., Li, C.L., Lin, H.T.: Re-benchmarking pool-based active learning for binary classification. arXiv (2023). https:\/\/doi.org\/10.48550\/ARXIV.2306.08954","DOI":"10.48550\/ARXIV.2306.08954"},{"issue":"8","key":"1_CR23","doi-asserted-by":"publisher","first-page":"3085","DOI":"10.1007\/s10994-022-06205-9","volume":"111","author":"PYA Paiva","year":"2022","unstructured":"Paiva, P.Y.A., Moreno, C.C., Smith-Miles, K., Valeriano, M.G., Lorena, A.C.: Relating instance hardness to classification performance in a dataset: a visual approach. Mach. Learn. 111(8), 3085\u20133123 (2022). https:\/\/doi.org\/10.1007\/s10994-022-06205-9","journal-title":"Mach. Learn."},{"key":"1_CR24","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR25","doi-asserted-by":"publisher","unstructured":"Pereira-Santos, D., Prud\u00eancio, R.B.C., de Carvalho, A.C.P.L.F.: Empirical investigation of active learning strategies. Neurocomputing 326\u2013327(15\u201327) (2019). https:\/\/doi.org\/10.1016\/j.neucom.2017.05.105.","DOI":"10.1016\/j.neucom.2017.05.105."},{"key":"1_CR26","unstructured":"Roy, N., McCallum, A.: Toward optimal active learning through sampling estimation of error reduction. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 441\u2013448 (2001)"},{"key":"1_CR27","doi-asserted-by":"publisher","unstructured":"Settles, B.: Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-031-01560-1","DOI":"10.1007\/978-3-031-01560-1"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Settles, B., Craven, M.: An analysis of active learning strategies for sequence labeling tasks. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 1070\u20131079 (2008)","DOI":"10.3115\/1613715.1613855"},{"issue":"2","key":"1_CR29","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10994-013-5422-z","volume":"95","author":"MR Smith","year":"2013","unstructured":"Smith, M.R., Martinez, T., Giraud-Carrier, C.: An instance level analysis of data complexity. Mach. Learn. 95(2), 225\u2013256 (2013). https:\/\/doi.org\/10.1007\/s10994-013-5422-z","journal-title":"Mach. Learn."},{"key":"1_CR30","doi-asserted-by":"publisher","unstructured":"Valeriano, M.G., Paiva, P.Y.A., Kiffer, C.R.V., Lorena, A.C.: A framework for characterizing what makes an instance hard to classify. In: 12th Brazilian Conference on Intelligent Systems (BRACIS 2023), pp. 353\u2013367 (2023). https:\/\/doi.org\/10.1007\/978-3-031-45389-2_24","DOI":"10.1007\/978-3-031-45389-2_24"},{"key":"1_CR31","doi-asserted-by":"publisher","unstructured":"Valeriano, M.G., Pereira, J.L.J., Kiffer, C.R.V., Lorena, A.C.: Explaining instances in the health domain based on the exploration of a dataset\u2019s hardness embedding. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, (GECCO 2024), pp. 1598\u20131606 (2024). https:\/\/doi.org\/10.1145\/3638530.3664113","DOI":"10.1145\/3638530.3664113"},{"key":"1_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/3-540-36618-0_28","volume-title":"Advances in Information Retrieval","author":"Z Xu","year":"2003","unstructured":"Xu, Z., Yu, K., Tresp, V., Xu, X., Wang, J.: Representative sampling for text classification using support vector machines. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol. 2633, pp. 393\u2013407. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36618-0_28"},{"key":"1_CR33","doi-asserted-by":"publisher","unstructured":"Zhan, X., Liu, H., Li, Q., Chan, A.B.: A comparative survey: benchmarking for pool-based active learning. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence(IJCAI-21), pp. 4679\u20134686 (2021). https:\/\/doi.org\/10.24963\/ijcai.2021\/634","DOI":"10.24963\/ijcai.2021\/634"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H.: The optimality of naive bayes. In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2004), pp. 562\u2013567 (2004)","DOI":"10.1109\/ICDM.2004.10030"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-15984-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:33:44Z","timestamp":1769718824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-15984-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032159830","9783032159847"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-15984-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fortaleza-CE","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bracis.sbc.org.br\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}