{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:58:02Z","timestamp":1776956282386,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,3,27]],"date-time":"2017-03-27T00:00:00Z","timestamp":1490572800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007316","name":"Klaus Tschira Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007316","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001664","name":"Leibniz-Gemeinschaft","doi-asserted-by":"publisher","award":["SAW-2015-LZI-2"],"award-info":[{"award-number":["SAW-2015-LZI-2"]}],"id":[{"id":"10.13039\/501100001664","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scientometrics"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s11192-017-2363-5","type":"journal-article","created":{"date-parts":[[2017,3,26]],"date-time":"2017-03-26T22:47:33Z","timestamp":1490568453000},"page":"1467-1500","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Data sets for author name disambiguation: an empirical analysis and a new resource"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5639-7682","authenticated-orcid":false,"given":"Mark-Christoph","family":"M\u00fcller","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Reitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,27]]},"reference":[{"key":"2363_CR1","unstructured":"Arehart, M., & Miller, K. J. (2008). A ground truth dataset for matching culturally diverse romanized person names. In Proceedings of the 6th international conference on language resources and evaluation, Marrakech, Morocco, 28\u201330 May 2008\u00a0(pp. 1136\u20131139)."},{"key":"2363_CR2","unstructured":"Bagga, A., & Baldwin, B. (1998). Algorithms for scoring coreference chains. In Proceedings of the 1st international conference on language resources and evaluation, Granada, Spain, 28\u201330 May 1998 (pp. 563\u2013566)."},{"issue":"11","key":"2363_CR3","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1002\/asi.23329","volume":"66","author":"L Bornmann","year":"2015","unstructured":"Bornmann, L., & Mutz, R. (2015). Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references. Journal of the Association for Information Science and Technology, 66(11), 2215\u20132222.","journal-title":"Journal of the Association for Information Science and Technology"},{"issue":"9","key":"2363_CR4","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1002\/asi.21363","volume":"61","author":"RG Cota","year":"2010","unstructured":"Cota, R. G., Ferreira, A. A., Nascimento, C., Gon\u00e7alves, M. A., & Laender, A. H. F. (2010). An unsupervised heuristic-based hierarchical method for name disambiguation in bibliographic citations. Journal of the American Society for Information Science and Technology, 61(9), 1853\u20131870.","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"2363_CR5","unstructured":"Culotta, A., Kanani, P., Hall, R., Wick, M., & McCallum, A. (2007). Author disambiguation using error-driven machine learning with a ranking loss function. In Proceedings of the sixth international workshop on information integration on the web, IIWeb \u201907 (pp. 32\u201337)."},{"key":"2363_CR6","unstructured":"Diesner, J., Evans, C. S., & Kim, J. (2015). Impact of entity disambiguation errors on social network properties. In Proceedings of the 9th international conference on web and social media, University of Oxford, Oxford, UK, 26\u201329\u00a0May 2015 (pp. 81\u201390)."},{"issue":"3","key":"2363_CR7","first-page":"293","volume":"5","author":"LVB Esperidi\u00e3o","year":"2014","unstructured":"Esperidi\u00e3o, L. V. B., Ferreira, A. A., Laender, A. H. F., Gon\u00e7alves, M. A., Gomes, D. M., Tavares, A. I., et al. (2014). Reducing fragmentation in incremental author name disambiguation. Journal of Information and Data Management, 5(3), 293\u2013307.","journal-title":"Journal of Information and Data Management"},{"issue":"2","key":"2363_CR8","first-page":"10:1","volume":"2","author":"X Fan","year":"2011","unstructured":"Fan, X., Jianyong Wang, X. P., Zhou, L., & Lv, B. (2011). On graph-based name disambiguation. Journal of Data and Information Quality, 2(2), 10:1\u201310:23.","journal-title":"Journal of Data and Information Quality"},{"issue":"2","key":"2363_CR9","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/2350036.2350040","volume":"41","author":"AA Ferreira","year":"2012","unstructured":"Ferreira, A. A., Gon\u00e7alves, M. A., & Laender, A. H. F. (2012a). A brief survey of automatic methods for author name disambiguation. SIGMOD Record, 41(2), 15\u201326.","journal-title":"SIGMOD Record"},{"key":"2363_CR10","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.ins.2012.04.022","volume":"206","author":"AA Ferreira","year":"2012","unstructured":"Ferreira, A. A., Gon\u00e7alves, M. A., Almeida, J. M., Laender, A. H. F., & Veloso, A. (2012b). A tool for generating synthetic authorship records for evaluating author name disambiguation methods. Information Sciences, 206, 42\u201362.","journal-title":"Information Sciences"},{"issue":"1","key":"2363_CR11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S1514-0326(10)60002-5","volume":"13","author":"BS Frey","year":"2010","unstructured":"Frey, B. S., & Rost, K. (2010). Do rankings reflect research quality? Journal of Applied Economics, 13(1), 1\u201338.","journal-title":"Journal of Applied Economics"},{"key":"2363_CR12","first-page":"129","volume":"108","author":"JW Grossman","year":"1995","unstructured":"Grossman, J. W., & Ion, P. D.\u00a0F. (1995). On a portion of the well-known collaboration graph. Congressus Numerantium, 108, 129\u2013132.","journal-title":"Congressus Numerantium"},{"key":"2363_CR13","doi-asserted-by":"crossref","unstructured":"Han, H., Giles, L., Zha, H., Li, C., & Tsioutsiouliklis, K. (2004). Two supervised learning approaches for name disambiguation in author citations. In Proceedings of the 4th ACM\/IEEE-CS joint conference on digital libraries, Tucson, AZ, USA, 7\u201311 June 2004 (pp. 296\u2013305).","DOI":"10.1145\/996350.996419"},{"key":"2363_CR14","doi-asserted-by":"crossref","unstructured":"Han, H., Xu, W., Zha, H., & Giles, C. L. (2005a). A hierarchical naive bayes mixture model for name disambiguation in author citations. In Proceedings of the 2005 ACM symposium on applied computing, Santa Fe, NM, USA, 13\u201317 March 2005 (pp. 1065\u20131069).","DOI":"10.1145\/1066677.1066920"},{"key":"2363_CR15","doi-asserted-by":"crossref","unstructured":"Han, H., Zha, H., & Giles, C. L. (2005b). Name disambiguation in author citations using a k-way spectral clustering method. In Proceedings of the 5th ACM\/IEEE-CS joint conference on digital libraries, Denver, CO, USA, 7\u201311 June 2005 (pp. 334\u2013343).","DOI":"10.1145\/1065385.1065462"},{"issue":"11","key":"2363_CR16","first-page":"118901\u20131\u2013118101","volume":"20","author":"G Jin-Zhong","year":"2011","unstructured":"Jin-Zhong, G., Qing-Hua, C., & You-Gui, W. (2011). Statistical distribution of chinese names. Chinese Physics B, 20(11), 118901\u20131\u2013118101\u20137.","journal-title":"Chinese Physics B"},{"key":"2363_CR17","first-page":"58","volume":"100","author":"M Jost","year":"2016","unstructured":"Jost, M., Roy, N. D., & Teschke, O. (2016). Another update on the collaboration graph. European Mathematical Society Newsletter, 100, 58\u201360.","journal-title":"European Mathematical Society Newsletter"},{"issue":"3","key":"2363_CR18","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1016\/j.ipm.2010.10.001","volume":"47","author":"I-S Kang","year":"2011","unstructured":"Kang, I.-S., Kim, P., Lee, S., Jung, H., & You, B.-J. (2011). Construction of a large-scale test set for author disambiguation. Information Processing & Management, 47(3), 452\u2013465.","journal-title":"Information Processing & Management"},{"issue":"6","key":"2363_CR19","doi-asserted-by":"crossref","first-page":"1446","DOI":"10.1002\/asi.23489","volume":"67","author":"J Kim","year":"2016","unstructured":"Kim, J., & Diesner, J. (2016). Distortive effects of initial-based name disambiguation on measurements of large-scale coauthorship networks. Journal of the Association for Information Science and Technology, 67(6), 1446\u20131461.","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"2363_CR20","doi-asserted-by":"crossref","unstructured":"Lee, D., On, B.-W., Kang, J., & Park, S. (2005). Effective and scalable solutions for mixed and split citation problems in digital libraries. In Proceedings of the 2nd international workshop on information quality in information systems, Baltimore, MD, USA, 17 June 2005 (pp. 69\u201376).","DOI":"10.1145\/1077501.1077514"},{"issue":"2","key":"2363_CR21","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.14778\/1687553.1687577","volume":"2","author":"M Ley","year":"2009","unstructured":"Ley, M. (2009). DBLP: Some lessons learned. Proceedings of the VLDB Endowment, 2(2), 1493\u20131500.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"2363_CR22","unstructured":"Ley, M., & Reuther, P. (2006). Maintaining an online bibliographical database: The problem of data quality. EGC 2006. Revue des Nouvelles Technologies de l\u2019Information, RNTI-E-6:5\u201310."},{"issue":"4","key":"2363_CR23","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1002\/asi.23063","volume":"65","author":"W Liu","year":"2014","unstructured":"Liu, W., Dogan, R. I., Kim, S., Comeau, D. C., Kim, W., Yeganova, L., et al. (2014). Author name disambiguation for PubMed. Journal of the Association for Information Science and Technology, 65(4), 765\u2013781.","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"2363_CR24","doi-asserted-by":"crossref","unstructured":"McKay, D., Sanchez, S., & Parker, R. (2010). What\u2019s my name again?: sociotechnical considerations for author name management in research databases. In Proceedings of the 22nd conference of the computer-human interaction special interest group of Australia on computer-human interaction, Brisbane, Australia, 22\u201326 November 2010\u00a0(pp. 240\u2013247).","DOI":"10.1145\/1952222.1952274"},{"key":"2363_CR25","unstructured":"Mihaljevic-Brandt, H., M\u00fcller, F., & Roy, N. (2014). Author profile pages in zbMATH\u2014Improving accuracy through user interaction. In Joint proceedings of the MathUI, OpenMath and ThEdu workshops and work in progress track at CICM, Coimbra, Portugal, 7\u201311 July 2014."},{"issue":"4","key":"2363_CR26","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1016\/j.joi.2013.06.006","volume":"7","author":"S Milojevi\u0107","year":"2013","unstructured":"Milojevi\u0107, S. (2013). Accuracy of simple, initials-based methods for author name disambiguation. Journal of Informetrics, 7(4), 767\u2013773.","journal-title":"Journal of Informetrics"},{"key":"2363_CR27","unstructured":"Ng, V. (2010). Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the 48th annual meeting of the association for computational linguistics, Uppsala, Sweden, 11\u201316 July 2010 (pp. 1396\u20131411)."},{"issue":"5","key":"2363_CR28","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/s10791-015-9261-3","volume":"18","author":"Y Qian","year":"2015","unstructured":"Qian, Y., Zheng, Q., Sakai, T., Ye, J., & Liu, J. (2015). Dynamic author name disambiguation for growing digital libraries. Information Retrieval Journal, 18(5), 379\u2013412.","journal-title":"Information Retrieval Journal"},{"key":"2363_CR29","doi-asserted-by":"crossref","unstructured":"Reitz, F., & Hoffmann, O. (2011). Did they notice?\u2014A case-study on the community contribution to data quality in DBLP. In S. Gradmann, F. Borri, C. Meghini & H. Schuldt (Eds.), Research and advanced technology for digital libraries\u2014International conference on theory and practice of digital libraries, TPDL 2011, Berlin, Germany, September 26-28, 2011. Proceedings, Vol. 6966, Lecture Notes in Computer Science (pp. 204\u2013215). Springer.","DOI":"10.1007\/978-3-642-24469-8_22"},{"key":"2363_CR30","unstructured":"Reuther, P. (2006). Personal name matching: New test collections and a social network based approach. Technical Report: Department for Databases and Information Systems, University of Trier, Trier, Germany."},{"issue":"3\u20134","key":"2363_CR31","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1080\/01639370902737232","volume":"47","author":"D Salo","year":"2009","unstructured":"Salo, D. (2009). Name authority control in institutional repositories. Cataloging & Classification Quarterly, 47(3\u20134), 249\u2013261.","journal-title":"Cataloging & Classification Quarterly"},{"issue":"3\u20134","key":"2363_CR32","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s00799-015-0158-y","volume":"16","author":"AF Santana","year":"2015","unstructured":"Santana, A. F., Gon\u00e7alves, M. A., Laender, A. H. F., & Ferreira, A. A. (2015). On the combination of domain-specific heuristics for author name disambiguation: the nearest cluster method. International Journal on Digital Libraries, 16(3\u20134), 229\u2013246.","journal-title":"International Journal on Digital Libraries"},{"issue":"1","key":"2363_CR33","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s11192-014-1289-4","volume":"100","author":"D Shin","year":"2014","unstructured":"Shin, D., Kim, T., Choi, J., & Kim, J. (2014). Author name disambiguation using a graph model with node splitting and merging based on bibliographic information. Scientometrics, 100(1), 15\u201350.","journal-title":"Scientometrics"},{"key":"2363_CR34","doi-asserted-by":"crossref","unstructured":"Song, Y., Huang, J., Councill, I. G., Li, J., & Giles, C. L. (2007). Efficient topic-based unsupervised name disambiguation. In Proceedings of the 7th ACM\/IEEE-CS joint conference on digital libraries, Vancouver, Canada, 18\u201323 June 2007 (pp. 342\u2013351).","DOI":"10.1145\/1255175.1255243"},{"key":"2363_CR35","first-page":"43","volume":"71","author":"O Teschke","year":"2009","unstructured":"Teschke, O. (2009). On authors and entities. European Mathematical Society Newsletter, 71, 43\u201344.","journal-title":"European Mathematical Society Newsletter"},{"key":"2363_CR36","first-page":"43","volume":"79","author":"O Teschke","year":"2011","unstructured":"Teschke, O., & Wegner, B. (2011). Author profiles at Zentralblatt MATH. European Mathematical Society Newsletter, 79, 43\u201344.","journal-title":"European Mathematical Society Newsletter"},{"key":"2363_CR37","doi-asserted-by":"crossref","unstructured":"Treeratpituk, P., & Giles, C. L. (2009). Disambiguating authors in academic publications using random forests. In Proceedings of the 9th ACM\/IEEE-CS joint conference on digital libraries, Austin, TX, USA, 15\u201319 June 2009\u00a0(pp. 39\u201348).","DOI":"10.1145\/1555400.1555408"},{"key":"2363_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Tang, J., Cheng, H., & Yu, P. S. (2011). ADANA: Active name disambiguation. In Proceedings of the 11th IEEE international conference on data mining, Vancouver, Canada, 11\u201314 December 2011 (pp. 794\u2013803).","DOI":"10.1109\/ICDM.2011.19"},{"issue":"1","key":"2363_CR39","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/s11192-005-0007-7","volume":"62","author":"P Weingart","year":"2005","unstructured":"Weingart, P. (2005). Impact of bibliometrics upon the science system: Inadvertent consequences? Scientometrics, 62(1), 117\u2013131.","journal-title":"Scientometrics"}],"container-title":["Scientometrics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11192-017-2363-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-017-2363-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-017-2363-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T01:59:12Z","timestamp":1568944752000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11192-017-2363-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,27]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["2363"],"URL":"https:\/\/doi.org\/10.1007\/s11192-017-2363-5","relation":{},"ISSN":["0138-9130","1588-2861"],"issn-type":[{"value":"0138-9130","type":"print"},{"value":"1588-2861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,27]]}}}