{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T02:49:07Z","timestamp":1725850147357},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319285597"},{"type":"electronic","value":"9783319285610"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-28561-0_3","type":"book-chapter","created":{"date-parts":[[2016,2,23]],"date-time":"2016-02-23T15:15:04Z","timestamp":1456240504000},"page":"25-35","source":"Crossref","is-referenced-by-count":3,"title":["Comparison of Text-Similarity Metrics for the Purpose of Identifying Identical Web Pages During Automated Web Application Testing"],"prefix":"10.1007","author":[{"given":"Marek","family":"Zachara","sequence":"first","affiliation":[]},{"given":"Dariusz","family":"Pa\u0142ka","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,2,24]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.entcs.2009.03.002","volume":"235","author":"M Alpuente","year":"2009","unstructured":"Alpuente, M., Romero, D.: A visual technique for web pages comparison. Electr. Notes Theor. Comput. Sci. 235, 3\u201318 (2009)","journal-title":"Electr. Notes Theor. Comput. Sci."},{"key":"3_CR2","unstructured":"Clayton R.: String Metrics Library: \n                    https:\/\/github.com\/rclayton\/StringSimilarity"},{"key":"3_CR3","unstructured":"Cohen W., Ravikumar P., Fienberg S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning, Vol. 3 (2003)"},{"issue":"4","key":"3_CR4","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TDSC.2006.50","volume":"3","author":"AY Fu","year":"2006","unstructured":"Fu, A.Y., Wenyin, L., Deng, X.: Detecting phishing web pages with visual similarity assessment based on earth mover\u2019s distance (EMD). IEEE Trans. Dependable Sec. Comput. 3(4), 301\u2013311 (2006)","journal-title":"IEEE Trans. Dependable Sec. Comput."},{"issue":"4","key":"3_CR5","first-page":"28","volume":"24","author":"L Gravano","year":"2001","unstructured":"Gravano, L., Ipeirotis, P.G., Jagadish, H.V., Koudas, N., Muthukrishnan, S., Pietarinen, L., Srivastava, D.: Using q-grams in a DBMS for approximate string processing. IEEE Data Eng. Bull. 24(4), 28\u201334 (2001)","journal-title":"IEEE Data Eng. Bull."},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Henzinger, M.: Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 284\u2013291. ACM (2006)","DOI":"10.1145\/1148170.1148222"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","volume":"11","author":"P Jaccard","year":"1912","unstructured":"Jaccard, P.: The distribution of the flora in the alpine zone. New Phytol. 11, 37\u201350 (1912)","journal-title":"New Phytol."},{"issue":"406","key":"3_CR8","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida. J. Am. Statist. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"J. Am. Statist. Assoc."},{"issue":"8","key":"3_CR9","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions and insertions and reversals. Soviet Physics Doklady 10(8), 707\u2013710 (1966)","journal-title":"Soviet Physics Doklady"},{"key":"3_CR10","unstructured":"Lucca, G.D., Penta, M.D., Fasolino, A.: An approach to identify duplicated web pages. In: Proceedings of International Computer Software and Applications Conference (COMPSAC), pp. 481\u2013486 (2002)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Lukashenko, R., Graudina, V., Grundspenkis, J.: Computer-based plagiarism detection methods and tools: an overview. In: CompSysTech. ACM International Conference Proceeding Series, Vol. 285, p. 40. ACM (2007)","DOI":"10.1145\/1330598.1330642"},{"issue":"1","key":"3_CR14","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/375360.375365","volume":"33","author":"G Navarro","year":"2001","unstructured":"Navarro, G.: A guided tour to approximate string matching. ACM Comput. Surv. 33(1), 31\u201388 (2001)","journal-title":"ACM Comput. Surv."},{"issue":"3","key":"3_CR15","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"SB Needleman","year":"1970","unstructured":"Needleman, S.B., Wunsch, C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48(3), 443\u2013453 (1970)","journal-title":"J. Mol. Biol."},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Pera, M.S., Ng, Y.K.: Identifying spam web pages based on content similarity. In: ICCSA (2), Vol. 5073, pp. 204\u2013219. Lecture Notes in Computer Science. Springer, Berlin (2008)","DOI":"10.1007\/978-3-540-69848-7_18"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Rosiello, A.P., Kirda, E., Kruegel, C., Ferrandi, F.: A layout-similarity based approach for detecting phishing pages. In: Security and Privacy in Communications Networks and the Workshops, pp. 454\u2013463. IEEE (2007)","DOI":"10.1109\/SECCOM.2007.4550367"},{"key":"3_CR18","unstructured":"SimMetrics, a Similarity Metric Library: \n                    http:\/\/sourceforge.net\/projects\/simmetrics\/"},{"issue":"1","key":"3_CR19","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"T Smith","year":"1981","unstructured":"Smith, T., Waterman, M.: Identification of common molecular subsequences. J. Mol. Biol. 147(1), 195\u2013197 (1981)","journal-title":"J. Mol. Biol."},{"issue":"4","key":"3_CR20","first-page":"1","volume":"5","author":"T Sorensen","year":"1948","unstructured":"Sorensen, T.: A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on Danish commons\u201d. Kongelige Danske Videnskabernes Selskab 5(4), 1\u201334 (1948)","journal-title":"Kongelige Danske Videnskabernes Selskab"},{"key":"3_CR21","unstructured":"Symantec Internet Security Threat Report, Vol. 20, \n                    http:\/\/www.symantec.com\/about\/news\/resources\/press_kits\/detail.jsp?pkid=istr-20\n                    \n                   (2015)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Wenyin, L., Huang, G., Xiaoyue, L., Min, Z., Deng, X.: Detection of phishing webpages based on visual similarity. In: 14th international conference on World Wide Web, pp. 1060\u20131061. ACM (2005)","DOI":"10.1145\/1062745.1062868"},{"key":"3_CR23","unstructured":"Winkler, W.E.: String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. In: Proceedings of the Section on Survey Research, pp. 354\u2013359 (1990)"},{"key":"3_CR24","unstructured":"Zachara M., Piskor-Ignatowicz C.: Comparison of string metrics effectiveness for the purpose of estimating the number of unique job offers. PAR (11), pp. 213\u2013216, PIAP (2011)"}],"container-title":["Advances in Intelligent Systems and Computing","Information Systems Architecture and Technology: Proceedings of 36th International Conference on Information Systems Architecture and Technology \u2013 ISAT 2015 \u2013 Part II"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-28561-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T15:32:40Z","timestamp":1559403160000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-28561-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319285597","9783319285610"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-28561-0_3","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2016]]}}}