{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:29:40Z","timestamp":1778149780444,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T00:00:00Z","timestamp":1711411200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T00:00:00Z","timestamp":1711411200000},"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":["J Intell Inf Syst"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s10844-024-00853-0","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T13:02:42Z","timestamp":1711458162000},"page":"1347-1373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ERABQS: entity resolution based on active machine learning and balancing query strategy"],"prefix":"10.1007","volume":"62","author":[{"given":"Jabrane","family":"Mourad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tabbaa","family":"Hiba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rochd","family":"Yassir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hafidi","family":"Imad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,26]]},"reference":[{"issue":"3","key":"853_CR1","doi-asserted-by":"publisher","first-page":"116","DOI":"10.3390\/info13030116","volume":"13","author":"T Alexakis","year":"2022","unstructured":"Alexakis, T., Peppes, N., Demestichas, K., et al. (2022). A machine learning-based method for content verification in the e-commerce domain. Information, 13(3), 116. https:\/\/doi.org\/10.3390\/info13030116","journal-title":"Information"},{"key":"853_CR2","doi-asserted-by":"publisher","unstructured":"Bahri, D., Jiang, H., Tay, Y., et\u00a0al. (2022). Scarf: Self-supervised contrastive learning using random feature corruption. arXiv:2106.15147. https:\/\/doi.org\/10.48550\/ARXIV.2106.15147","DOI":"10.48550\/ARXIV.2106.15147"},{"issue":"9","key":"853_CR3","doi-asserted-by":"publisher","first-page":"2305","DOI":"10.1109\/tkde.2015.2416734","volume":"27","author":"GD Bianco","year":"2015","unstructured":"Bianco, G. D., Galante, R., Goncalves, M. A., et al. (2015). A practical and effective sampling selection strategy for large scale deduplication. IEEE Transactions on Knowledge and Data Engineering, 27(9), 2305\u20132319. https:\/\/doi.org\/10.1109\/tkde.2015.2416734","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"853_CR4","doi-asserted-by":"publisher","unstructured":"Brunner, U., & Stockinger, K. (2020). Entity matching with transformer architectures - a step forward in data integration. OpenProceedings. https:\/\/doi.org\/10.21256\/ZHAW-19637","DOI":"10.21256\/ZHAW-19637"},{"issue":"2","key":"853_CR5","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.1007\/s11227-021-03966-3","volume":"78","author":"A Chen","year":"2021","unstructured":"Chen, A., Yang, P., & Cheng, P. (2021). ACTSSD: social spammer detection based on active learning and co-training. The Journal of Supercomputing, 78(2), 2744\u20132771. https:\/\/doi.org\/10.1007\/s11227-021-03966-3","journal-title":"The Journal of Supercomputing"},{"issue":"04","key":"853_CR6","doi-asserted-by":"publisher","first-page":"3438","DOI":"10.1609\/aaai.v34i04.5747","volume":"34","author":"D Chen","year":"2020","unstructured":"Chen, D., Lin, Y., Li, W., et al. (2020). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 3438\u20133445. https:\/\/doi.org\/10.1609\/aaai.v34i04.5747","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"853_CR7","doi-asserted-by":"publisher","unstructured":"Chen, R., Shen, Y., & Zhang, D. (2021). GNEM: A generic one-to-set neural entity matching framework. In: Proceedings of the Web Conference 2021. ACM. https:\/\/doi.org\/10.1145\/3442381.3450119","DOI":"10.1145\/3442381.3450119"},{"key":"853_CR8","doi-asserted-by":"publisher","unstructured":"Chen, Z., Chen, Q., Hou, B., et\u00a0al. (2020). Towards interpretable and learnable risk analysis for entity resolution. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3318464.3380572","DOI":"10.1145\/3318464.3380572"},{"key":"853_CR9","doi-asserted-by":"publisher","unstructured":"Christen, P., Vatsalan, D., & Wang, Q. (2015). Efficient entity resolution with adaptive and interactive training data selection. In: 2015 IEEE International Conference on Data Mining. IEEE. https:\/\/doi.org\/10.1109\/icdm.2015.63","DOI":"10.1109\/icdm.2015.63"},{"issue":"6","key":"853_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2021","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., et al. (2021). An overview of end-to-end entity resolution for big data. ACM Computing Surveys, 53(6), 1\u201342. https:\/\/doi.org\/10.1145\/3418896","journal-title":"ACM Computing Surveys"},{"key":"853_CR11","doi-asserted-by":"publisher","unstructured":"Dharavath, R., & Singh, A.K. (2015). Entity Resolution-Based Jaccard Similarity Coefficient for Heterogeneous Distributed Databases (pp. 497\u2013507) Springer India. https:\/\/doi.org\/10.1007\/978-81-322-2517-1_48","DOI":"10.1007\/978-81-322-2517-1_48"},{"key":"853_CR12","doi-asserted-by":"publisher","unstructured":"Dong, X. L., & Rekatsinas, T. (2018). Data integration and machine learning. In: Proceedings of the 2018 International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3183713.3197387","DOI":"10.1145\/3183713.3197387"},{"key":"853_CR13","doi-asserted-by":"publisher","unstructured":"Fu, C., Han, X., He, J., et\u00a0al. (2020). Hierarchical matching network for heterogeneous entity resolution. In: C. Bessiere (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20 (pp. 3665\u20133671). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2020\/507. main track","DOI":"10.24963\/ijcai.2020\/507"},{"key":"853_CR14","doi-asserted-by":"publisher","unstructured":"Getoor, L., & Machanavajjhala, A. (2012). Entity resolution. Proceedings of the VLDB Endowment, 5(12), 2018\u20132019. https:\/\/doi.org\/10.14778\/2367502.2367564","DOI":"10.14778\/2367502.2367564"},{"issue":"3","key":"853_CR15","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s11222-017-9746-6","volume":"28","author":"D Hand","year":"2017","unstructured":"Hand, D., & Christen, P. (2017). Using the f-measure for evaluating record linkage algorithms. Statistics and Computing, 28(3), 539\u2013547. https:\/\/doi.org\/10.1007\/s11222-017-9746-6","journal-title":"Statistics and Computing"},{"key":"853_CR16","doi-asserted-by":"publisher","unstructured":"Helgertz, J., Price, J., Wellington, J., et\u00a0al. (2021). A new strategy for linking U.S. historical censuses: A case study for the IPUMS multigenerational longitudinal panel. Historical Methods: A Journal of Quantitative and Interdisciplinary History, 55(1), 12\u201329. https:\/\/doi.org\/10.1080\/01615440.2021.1985027","DOI":"10.1080\/01615440.2021.1985027"},{"key":"853_CR17","doi-asserted-by":"publisher","unstructured":"Hou, B., Chenm, Q., Shen, J., et\u00a0al. (2019). Gradual machine learning for entity resolution. In: The World Wide Web Conference. ACM. https:\/\/doi.org\/10.1145\/3308558.3314121","DOI":"10.1145\/3308558.3314121"},{"key":"853_CR18","doi-asserted-by":"publisher","unstructured":"Jain, A., Sarawagi, S., & Sen, P. (2021). Deep indexed active learning for matching heterogeneous entity representations. Proceedings of the VLDB Endowment, 15(1), 31\u201345. https:\/\/doi.org\/10.14778\/3485450.3485455","DOI":"10.14778\/3485450.3485455"},{"issue":"406","key":"853_CR19","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M. A. (1989). Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Association, 84(406), 414\u2013420. https:\/\/doi.org\/10.1080\/01621459.1989.10478785","journal-title":"Journal of the American Statistical Association"},{"key":"853_CR20","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.is.2017.06.006","volume":"71","author":"A Jurek","year":"2017","unstructured":"Jurek, A., Hong, J., Chi, Y., et al. (2017). A novel ensemble learning approach to unsupervised record linkage. Information Systems, 71, 40\u201354. https:\/\/doi.org\/10.1016\/j.is.2017.06.006","journal-title":"Information Systems"},{"key":"853_CR21","unstructured":"Levenshtein, V. I. (1965). Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady, 10, 707\u2013710. https:\/\/api.semanticscholar.org\/CorpusID:60827152"},{"key":"853_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-022-00773-x","author":"S Li","year":"2023","unstructured":"Li, S., & Wu, H. (2023). Transformer-based denoising adversarial variational entity resolution. Journal of Intelligent Information Systems. https:\/\/doi.org\/10.1007\/s10844-022-00773-x","journal-title":"Journal of Intelligent Information Systems"},{"key":"853_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-023-00779-z","author":"Y Li","year":"2023","unstructured":"Li, Y., Li, J., Suhara, Y., et al. (2023). Effective entity matching with transformers. The VLDB Journal. https:\/\/doi.org\/10.1007\/s00778-023-00779-z","journal-title":"The VLDB Journal"},{"key":"853_CR24","doi-asserted-by":"publisher","unstructured":"Meduri, V. V., Popa, L., Sen, P., et\u00a0al. (2020). A comprehensive benchmark framework for active learning methods in entity matching. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3318464.3380597","DOI":"10.1145\/3318464.3380597"},{"key":"853_CR25","doi-asserted-by":"publisher","unstructured":"Mozafari, B., Sarkar, P., Franklin, M., et\u00a0al. (2014). Scaling up crowd-sourcing to very large datasets. Proceedings of the VLDB Endowment, 8(2), 125\u2013136. https:\/\/doi.org\/10.14778\/2735471.2735474","DOI":"10.14778\/2735471.2735474"},{"key":"853_CR26","doi-asserted-by":"publisher","unstructured":"Mudgal, S., Li, H., Rekatsinas, T., et\u00a0al. (2018). Deep learning for entity matching. In: Proceedings of the 2018 International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3183713.3196926","DOI":"10.1145\/3183713.3196926"},{"key":"853_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107729","volume":"236","author":"Y Nafa","year":"2022","unstructured":"Nafa, Y., Chen, Q., Chen, Z., et al. (2022). Active deep learning on entity resolution by risk sampling. Knowledge-Based Systems, 236, 107729. https:\/\/doi.org\/10.1016\/j.knosys.2021.107729","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"853_CR28","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s10844-021-00676-3","volume":"58","author":"M Niknam","year":"2021","unstructured":"Niknam, M., Minaei-Bidgoli, B., & Dianat, R. (2021). The role of transitive closure in evaluating blocking methods for dirty entity resolution. Journal of Intelligent Information Systems, 58(3), 561\u2013590. https:\/\/doi.org\/10.1007\/s10844-021-00676-3","journal-title":"Journal of Intelligent Information Systems"},{"key":"853_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01878-7","author":"G Papadakis","year":"2021","unstructured":"Papadakis, G., Ioannou, E., Thanos, E., et al. (2021). The Four Generations of Entity Resolution. Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-031-01878-7","journal-title":"Springer International Publishing"},{"key":"853_CR30","doi-asserted-by":"publisher","unstructured":"Papadakis, G., Kirielle, N., Christen, P., et\u00a0al. (2023). A critical re-evaluation of benchmark datasets for (deep) learning-based matching algorithms. https:\/\/doi.org\/10.48550\/ARXIV.2307.01231","DOI":"10.48550\/ARXIV.2307.01231"},{"key":"853_CR31","doi-asserted-by":"publisher","unstructured":"Peeters, R., & Bizer, C. (2021). Dual-objective fine-tuning of BERT for entity matching. Proceedings of the VLDB Endowment, 14(10), 1913\u20131921. https:\/\/doi.org\/10.14778\/3467861.3467878","DOI":"10.14778\/3467861.3467878"},{"issue":"3","key":"853_CR32","doi-asserted-by":"publisher","first-page":"549","DOI":"10.3233\/sw-190356","volume":"11","author":"P Petrovski","year":"2020","unstructured":"Petrovski, P., & Bizer, C. (2020). Learning expressive linkage rules from sparse data. Semantic Web, 11(3), 549\u2013567. https:\/\/doi.org\/10.3233\/sw-190356","journal-title":"Semantic Web"},{"key":"853_CR33","doi-asserted-by":"publisher","unstructured":"Petrovski, P., Primpeli, A., Meusel, R., et\u00a0al. (2017). The wdc gold standards for product feature extraction and matching. In: D. Bridge, H. Stuckenschmidt (eds.) E-Commerce and Web Technologies (pp. 73\u201386). Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-319-53676-7_6","DOI":"10.1007\/978-3-319-53676-7_6"},{"key":"853_CR34","doi-asserted-by":"publisher","unstructured":"Primpeli, A., Bizer, C., & Keuper, M. (2020). Unsupervised bootstrapping of active learning for entity resolution. In: The Semantic Web (pp. 215\u2013231). Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-030-49461-2_13","DOI":"10.1007\/978-3-030-49461-2_13"},{"key":"853_CR35","doi-asserted-by":"publisher","unstructured":"Qian, K., Popa, L., & Sen, P. (2017). Active learning for large-scale entity resolution. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM. https:\/\/doi.org\/10.1145\/3132847.3132949","DOI":"10.1145\/3132847.3132949"},{"key":"853_CR36","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.datak.2017.10.004","volume":"112","author":"OF Reyes-Galaviz","year":"2017","unstructured":"Reyes-Galaviz, O. F., Pedrycz, W., He, Z., et al. (2017). A supervised gradient-based learning algorithm for optimized entity resolution. Data & Knowledge Engineering, 112, 106\u2013129. https:\/\/doi.org\/10.1016\/j.datak.2017.10.004","journal-title":"Data & Knowledge Engineering"},{"key":"853_CR37","doi-asserted-by":"publisher","unstructured":"Sarawagi, S., & Bhamidipaty, A. (2002). Interactive deduplication using active learning. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD\u201902. ACM Press. https:\/\/doi.org\/10.1145\/775047.775087","DOI":"10.1145\/775047.775087"},{"key":"853_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01560-1","author":"B Settles","year":"2012","unstructured":"Settles, B. (2012). Active Learning. Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-031-01560-1","journal-title":"Springer International Publishing"},{"issue":"3","key":"853_CR39","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C. E. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27(3), 379\u2013423. https:\/\/doi.org\/10.1002\/j.1538-7305.1948.tb01338.x","journal-title":"The Bell System Technical Journal"},{"key":"853_CR40","doi-asserted-by":"publisher","unstructured":"Somepalli, G., Goldblum, M., Schwarzschild, A., et\u00a0al. (2021). Saint: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv:2106.01342. https:\/\/doi.org\/10.48550\/ARXIV.2106.01342","DOI":"10.48550\/ARXIV.2106.01342"},{"key":"853_CR41","doi-asserted-by":"publisher","unstructured":"Tejada, S., Knoblock, C. A., & Minton, S. (2002). Learning domain-independent string transformation weights for high accuracy object identification. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM. https:\/\/doi.org\/10.1145\/775047.775099","DOI":"10.1145\/775047.775099"},{"issue":"2","key":"853_CR42","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/s10844-019-00544-1","volume":"52","author":"PKM Vieira","year":"2019","unstructured":"Vieira, P. K. M., L\u00f3scio, B. F., & Salgado, A. C. (2019). Incremental entity resolution process over query results for data integration systems. Journal of Intelligent Information Systems, 52(2), 451\u2013471. https:\/\/doi.org\/10.1007\/s10844-019-00544-1","journal-title":"Journal of Intelligent Information Systems"},{"key":"853_CR43","doi-asserted-by":"publisher","unstructured":"Wu, R., Chaba, S., Sawlani, S., et\u00a0al. (2020). ZeroER: Entity resolution using zero labeled examples. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3318464.3389743","DOI":"10.1145\/3318464.3389743"},{"key":"853_CR44","doi-asserted-by":"publisher","unstructured":"Yan, Y., Meyles, S., Haghighi, A., et\u00a0al. (2020). Entity matching in the wild: A consistent and versatile framework to unify data in industrial applications. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. ACM. https:\/\/doi.org\/10.1145\/3318464.3386143","DOI":"10.1145\/3318464.3386143"},{"key":"853_CR45","doi-asserted-by":"publisher","unstructured":"Zhang, D., Guo, L., He, X., et\u00a0al. (2018). A graph-theoretic fusion framework for unsupervised entity resolution. In: 2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE. https:\/\/doi.org\/10.1109\/icde.2018.00070","DOI":"10.1109\/icde.2018.00070"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-024-00853-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-024-00853-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-024-00853-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T09:04:12Z","timestamp":1730365452000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-024-00853-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,26]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["853"],"URL":"https:\/\/doi.org\/10.1007\/s10844-024-00853-0","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,26]]},"assertion":[{"value":"7 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"All authors agree with the content and give explicit consent to submit.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}