{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:52:58Z","timestamp":1706755978442},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,7,15]],"date-time":"2016-07-15T00:00:00Z","timestamp":1468540800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,7,15]],"date-time":"2016-07-15T00:00:00Z","timestamp":1468540800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scientometrics"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s11192-016-2066-3","type":"journal-article","created":{"date-parts":[[2016,7,15]],"date-time":"2016-07-15T12:45:09Z","timestamp":1468586709000},"page":"1525-1546","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Using character n-grams to match a list of publications to references in bibliographic databases"],"prefix":"10.1007","volume":"109","author":[{"given":"Mehmet Ali","family":"Abdulhayoglu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bart","family":"Thijs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wouter","family":"Jeuris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,7,15]]},"reference":[{"key":"2066_CR1","unstructured":"Abdulhayoglu, M. A., & Thijs, B. (2013). Matching bibliometric data from publication lists with large databases using n-grams. In Proceedings of 14th international society of scientometrics and informetrics conference (ISSI-2013), Vienna, Austria, Vol. 2, pp. 1151\u20131158."},{"key":"2066_CR2","unstructured":"Abou-Assaleh, T., Cercone, N., Keselj, V., & Sweidan, R. (2004). Detection of new malicious code using n-grams signatures. In PST, pp. 193\u2013196."},{"key":"2066_CR3","unstructured":"Apache Lucene. (2014). http:\/\/lucene.apache.org. Accessed 2014."},{"issue":"5","key":"2066_CR4","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MIS.2003.1234765","volume":"18","author":"M Bilenko","year":"2003","unstructured":"Bilenko, M., Mooney, R., Cohen, W., Ravikumar, P., & Fienberg, S. (2003). Adaptive name matching in information integration. IEEE Intelligent Systems, 18(5), 16\u201323.","journal-title":"IEEE Intelligent Systems"},{"key":"2066_CR5","unstructured":"Cavnar, W. B. (1993). n-Gram-based text filtering for TREC-2. Ann Arbor, 1001, 48113-4001."},{"key":"2066_CR6","unstructured":"Cavnar, W. B., & Trenkle, J. M. (1994). n-Gram-based text categorization. In Proceedings of SDAIR-94, 3rd annual symposium on document analysis and information retrieval, Las Vegas, US, pp. 161\u2013175."},{"key":"2066_CR7","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1002\/(SICI)1097-4571(199504)46:3<162::AID-ASI2>3.0.CO;2-6","volume":"46","author":"JD Cohen","year":"1995","unstructured":"Cohen, J. D. (1995). Highlights: Language- and domain-independent automatic indexing terms for abstracting. Journal of the American Society for Information Science, 46, 162\u2013174.","journal-title":"Journal of the American Society for Information Science"},{"key":"2066_CR8","unstructured":"Cohen, W., Ravikumar, P., & Fienberg, S. (2003). A comparison of string metrics for matching names and records. In KDD workshop on data cleaning and object consolidation (Vol. 3, pp. 73\u201378)."},{"issue":"1","key":"2066_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A. K., Ipeirotis, P. G., & Verykios, V. S. (2007). Duplicate record detection: A survey. IEEE Transactions on Knowledge and Data Engineering, 19(1), 1\u201316.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2066_CR10","first-page":"99","volume":"238","author":"J Fisher","year":"2013","unstructured":"Fisher, J., Wang, Q., Wong, P., & Christen, P. (2013). Data cleaning and matching of institutions in bibliographic databases. Organization, 238, 99\u2013103.","journal-title":"Organization"},{"issue":"6","key":"2066_CR11","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.ipm.2014.06.005","volume":"50","author":"BC Gencosman","year":"2014","unstructured":"Gencosman, B. C., Ozmutlu, H. C., & Ozmutlu, S. (2014). Character n-gram application for automatic new topic identification. Information Processing and Management, 50(6), 821\u2013856.","journal-title":"Information Processing and Management"},{"key":"2066_CR12","doi-asserted-by":"crossref","unstructured":"Giles, C. L., Bollacker, K. D., & Lawrence, S. (1998). CiteSeer: An automatic citation indexing system. In Digital 98 libraries. Third ACM conference on digital libraries, pp. 89\u201398.","DOI":"10.1145\/276675.276685"},{"issue":"2","key":"2066_CR13","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/BF02093621","volume":"37","author":"W Gl\u00e4nzel","year":"1996","unstructured":"Gl\u00e4nzel, W., & Czerwon, H. J. (1996). A new methodological approach to bibliographic coupling and its application to the national, regional and institutional level. Scientometrics, 37(2), 195\u2013221.","journal-title":"Scientometrics"},{"issue":"2","key":"2066_CR14","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/BF02018107","volume":"30","author":"W Gl\u00e4nzel","year":"1994","unstructured":"Gl\u00e4nzel, W., & Schoepflin, U. (1994). Little scientometrics, big scientometrics\u2026 and beyond? Scientometrics, 30(2), 375\u2013384.","journal-title":"Scientometrics"},{"key":"2066_CR15","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/978-3-540-68125-0_87","volume-title":"Advances in knowledge discovery and data mining","author":"C Gong","year":"2008","unstructured":"Gong, C., Huang, Y., Cheng, X., & Bai, S. (2008). Detecting near-duplicates in large-scale short text databases. In Washio, T., Suzuki, E., Ting, K. M., Inokuchi, A. (Eds.), Advances in knowledge discovery and data mining (pp. 877\u2013883). Berlin: Springer."},{"key":"2066_CR16","doi-asserted-by":"crossref","unstructured":"J\u00e4rvelin, A., Talvensaari, T., & J\u00e4rvelin, A. (2008). Data driven methods for improving mono-and cross-lingual IR performance in noisy environments. In  Proceedings of the second workshop on analytics for noisy unstructured text data (pp. 75\u201382).","DOI":"10.1145\/1390749.1390762"},{"issue":"6","key":"2066_CR17","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1142\/S0218213007003692","volume":"16","author":"I Kanaris","year":"2007","unstructured":"Kanaris, I., Kanaris, K., Houvardas, I., & Stamatatos, E. (2007). Words versus character n-grams for anti-spam filtering. International Journal on Artificial Intelligence Tools, 16(6), 1047\u20131067.","journal-title":"International Journal on Artificial Intelligence Tools"},{"key":"2066_CR18","unstructured":"Ke\u0161elj, V., Peng, F., Cercone, N., & Thomas, C. (2003). n-Gram-based author profiles for authorship attribution. In Proceedings of the conference pacific association for computational linguistics, PACLING, 3 (pp. 255\u2013264)."},{"key":"2066_CR19","doi-asserted-by":"crossref","unstructured":"Kondrak, G. (2005). n-Gram similarity and distance. In Proceedings of the twelfth international conference on string processing and information retrieval (SPIRE 2005), Buenos Aires, Argentina, pp. 115\u2013126.","DOI":"10.1007\/11575832_13"},{"key":"2066_CR20","unstructured":"Larsen, B. (2004). References and citations in automatic indexing and retrieval systems\u2014Experiments with the boomerang effect. PhD thesis, Royal School of Library and Information Science."},{"key":"2066_CR21","unstructured":"Lawrence, S., Giles, C. L., & Bollacker, K. D. (1999). Autonomous citation matching. In Etzioni, O., Muller, J. P., & Bradshaw, J. M. (eds.), AGENTS\u201999. Proceedings of the third annual conference on autonomous agents, May 1\u20135, 1999, Seattle, WA, USA (pp. 392\u2013393). New York: ACM Press."},{"key":"2066_CR22","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V. I. (1966). Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics-Doklady, 10, 707\u2013710.","journal-title":"Soviet Physics-Doklady"},{"key":"2066_CR23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C. D., Raghavan, P., & Sch\u00fctze, H. (2008). Introduction to information retrieval. Cambridge: Cambridge University Press."},{"key":"2066_CR24","unstructured":"MATLAB Release. (2014). The MathWorks, Inc., Natick, Massachusetts, USA."},{"key":"2066_CR25","doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., & Ungar, L. H. (2000). Efficient clustering of high-dimensional data sets with application to reference matching. In Proceedings of the sixth ACM SIGKDD international conference on knowledge discovery and data mining (pp. 169\u2013178).","DOI":"10.1145\/347090.347123"},{"key":"2066_CR26","unstructured":"McNamee, P. (2008). Textual representations for corpus-based bilingual retrieval. PhD thesis, University of Maryland (Baltimore County)."},{"issue":"1\u20132","key":"2066_CR27","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P Mcnamee","year":"2004","unstructured":"Mcnamee, P., & Mayfield, J. (2004). Character n-gram tokenization for European language text retrieval. Information Retrieval, 7(1\u20132), 73\u201397.","journal-title":"Information Retrieval"},{"key":"2066_CR28","doi-asserted-by":"crossref","unstructured":"Miao, Y., Ke\u0161elj, V., & Milios, E. (2005). Document clustering using character n-grams: a comparative evaluation with term-based and word-based clustering. In Proceedings of the 14th ACM international conference on information and knowledge management (pp. 357\u2013358).","DOI":"10.1145\/1099554.1099665"},{"key":"2066_CR29","doi-asserted-by":"crossref","unstructured":"Mihalcea, R., & Nastase, V. (2002). Letter level learning for language independent diacritics restoration. In Proceedings of the 6th conference on natural language learning (CoNLL) (105\u2013111).","DOI":"10.3115\/1118853.1118874"},{"issue":"4","key":"2066_CR30","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/j.ipm.2004.02.003","volume":"41","author":"SH Mustafa","year":"2005","unstructured":"Mustafa, S. H. (2005). Character contiguity in n-gram-based word matching: The case for Arabic text searching. Information Processing and Management, 41(4), 819\u2013827.","journal-title":"Information Processing and Management"},{"key":"2066_CR31","first-page":"1401","volume-title":"Advances in neural information processing systems. Conference on neural information processing systems","author":"H Pasula","year":"2002","unstructured":"Pasula, H., Marthi, B., Milch, B., Russell, S., & Shpitser, I. (2002). Identity uncertainty and citation matching. In Weiss, Y. (Ed.), Advances in neural information processing systems. Conference on neural information processing systems (pp. 1401\u20131408). British Columbia: MIT Press."},{"key":"2066_CR32","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/978-3-540-72035-5-27","volume-title":"BIS 2007. LNCS","author":"J Piskorski","year":"2007","unstructured":"Piskorski, J., & Sydow, M. (2007). String distance metrics for reference matching and search query correction. In W. Abramowicz (Ed.), BIS 2007. LNCS (Vol. 4439, pp. 353\u2013365). Eidelberg: Springer. doi:10.1007\/978-3-540-72035-5-27."},{"key":"2066_CR33","doi-asserted-by":"crossref","unstructured":"Qu, S., Wang, S., & Zou, Y. (2008). Improvement of text feature selection method based on tfidf. In Future information technology and management engineering (pp. 79\u201381).","DOI":"10.1109\/FITME.2008.25"},{"issue":"2","key":"2066_CR34","first-page":"78","volume":"30","author":"SK Sen","year":"1983","unstructured":"Sen, S. K., & Gan, S. K. (1983). A mathematical extension of the idea of bibliographic coupling and its applications. Annals of Library Science and Documentation, 30(2), 78\u201382.","journal-title":"Annals of Library Science and Documentation"},{"issue":"2","key":"2066_CR35","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.cmpb.2005.11.007","volume":"81","author":"A Tomovi\u0107","year":"2006","unstructured":"Tomovi\u0107, A., Jani\u010di\u0107, P., & Ke\u0161elj, V. (2006). n-Gram-based classification and unsupervised hierarchical clustering of genome sequences. Computer Methods and Programs in Biomedicine, 81(2), 137\u2013153.","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"1","key":"2066_CR36","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/BF02461131","volume":"38","author":"AFJ Van Raan","year":"1997","unstructured":"Van Raan, A. F. J. (1997). Scientometrics: state-of-the-art. Scientometrics, 38(1), 205\u2013218.","journal-title":"Scientometrics"},{"issue":"2","key":"2066_CR37","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.ipm.2010.08.004","volume":"47","author":"J Vilares","year":"2011","unstructured":"Vilares, J., Vilares, M., & Otero, J. (2011). Managing misspelled queries in IR applications. Information Processing and Management, 47(2), 263\u2013286.","journal-title":"Information Processing and Management"},{"key":"2066_CR38","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/0306-4573(81)90044-3","volume":"17","author":"EM Zamora","year":"1981","unstructured":"Zamora, E. M., Pollock, J. J., & Zamora, A. (1981). The use of trigram analysis for spelling error detection. Information Processing and Management, 17, 305\u2013316.","journal-title":"Information Processing and Management"}],"container-title":["Scientometrics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11192-016-2066-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-016-2066-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-016-2066-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T09:03:40Z","timestamp":1610010220000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11192-016-2066-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,15]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["2066"],"URL":"https:\/\/doi.org\/10.1007\/s11192-016-2066-3","relation":{},"ISSN":["0138-9130","1588-2861"],"issn-type":[{"value":"0138-9130","type":"print"},{"value":"1588-2861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,15]]},"assertion":[{"value":"22 January 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2016","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}