{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:45:15Z","timestamp":1755999915721},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,5,9]],"date-time":"2017-05-09T00:00:00Z","timestamp":1494288000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1007\/s10115-017-1062-0","type":"journal-article","created":{"date-parts":[[2017,5,9]],"date-time":"2017-05-09T03:58:50Z","timestamp":1494302330000},"page":"305-331","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["STEM: a suffix tree-based method for web data records extraction"],"prefix":"10.1007","volume":"55","author":[{"given":"Yixiang","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reynold","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,9]]},"reference":[{"key":"1062_CR1","doi-asserted-by":"crossref","unstructured":"Laender A, Riberro-Neto B, Silva A, Teixira J (2002) A brief survey of web data extraction tools. In: SIGMOD record, vol 31(2). ACM, New York, pp 84\u201393","DOI":"10.1145\/565117.565137"},{"issue":"10","key":"1062_CR2","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"C-H Chang","year":"2006","unstructured":"Chang C-H, Kayed M, Girgis MR, Shaala KF (2006) A survey of web information extraction systems. IEEE Trans Knowl Data Eng. 18(10):1411\u20131428","journal-title":"IEEE Trans Knowl Data Eng."},{"issue":"9","key":"1062_CR3","doi-asserted-by":"crossref","first-page":"1960","DOI":"10.1109\/TKDE.2012.135","volume":"25","author":"H Sleiman","year":"2013","unstructured":"Sleiman H, Corchuelo R et al (2013) A survey on region extractors from web documents. IEEE Trans Knowl Data Eng 25(9):1960\u20131981","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1062_CR4","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.knosys.2014.07.007","volume":"70","author":"E Ferrara","year":"2014","unstructured":"Ferrara E, De Meo P, Fiumara G, Baumgartner R (2014) Web data extraction, applications and techniques: a survey. Knowl Based Syst 70:301\u2013323","journal-title":"Knowl Based Syst"},{"key":"1062_CR5","doi-asserted-by":"crossref","unstructured":"Miao G, Tatemura J, Hsiung W-P, Sawires A, Moser L (2009) Extracting data records from the web using tag path clustering. In: Proceedings of the 18th international conference on World Wide Web (WWW). ACM, New York, pp 981\u2013990","DOI":"10.1145\/1526709.1526841"},{"issue":"7","key":"1062_CR6","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1109\/TKDE.2011.66","volume":"24","author":"W Su","year":"2012","unstructured":"Su W, Wang J, Wang J, Lochovsky FH, Liu Y (2012) Combing tag and value similarity for data extraction and alignment. IEEE Trans Knowl Data Eng 24(7):1186\u20131200","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1062_CR7","doi-asserted-by":"crossref","unstructured":"Liu B, Grossman R, Zhai Y (2003) Mining data records in web pages. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining. ACM, New York, pp 601\u2013606","DOI":"10.1145\/956750.956826"},{"issue":"2","key":"1062_CR8","doi-asserted-by":"crossref","first-page":"1512","DOI":"10.14778\/1687553.1687580","volume":"2","author":"R Baumgartner","year":"2009","unstructured":"Baumgartner R, Gottlob G, Herzog M (2009) Scalable web data extraction for online market intelligence. Proc VLDB Endow 2(2):1512\u20131523","journal-title":"Proc VLDB Endow"},{"key":"1062_CR9","doi-asserted-by":"crossref","unstructured":"Liu L, Pu C, Han W (2000) Xwrap: an xml-enabled wrapper construction system for web information sources. In: Proceedings of the IEEE 16th international conference on data engineering, pp 611\u2013621","DOI":"10.1109\/ICDE.2000.839475"},{"key":"1062_CR10","doi-asserted-by":"crossref","unstructured":"Gulhane P, Madaan A, Mehta R, et al (2011) Web-scale information extraction with vertex. In: ICDE, pp 209\u2013220","DOI":"10.1109\/ICDE.2011.5767842"},{"key":"1062_CR11","doi-asserted-by":"crossref","unstructured":"Etzioni O, Cafarella M, Downey D, Kok S, Popescu A-M, Shaked T, Soderland S, Weld DS, Yates A (2004) Web-scale information extraction in knowitall (preliminary results). In: Proceedings of the 13th international conference on World Wide Web. ACM, New York, pp 100\u2013110","DOI":"10.1145\/988672.988687"},{"key":"1062_CR12","doi-asserted-by":"crossref","unstructured":"Gupta S, Kaiser G, Neistadt D, Grimm P (2003) Dom-based content extraction of html documents. In: Proceedings of the 12th international conference on World Wide Web, pp 207\u2013214","DOI":"10.1145\/775152.775182"},{"key":"1062_CR13","doi-asserted-by":"crossref","unstructured":"Gupta S, Kaiser GE, Grimm P, Chiang MF, Starren J (2005) Automating content extraction of html documents. In: Proceedings of the 14th international conference on World Wide Web, vol\u00a08, no.\u00a02, pp 179\u2013224, 6","DOI":"10.1007\/s11280-004-4873-3"},{"key":"1062_CR14","doi-asserted-by":"crossref","unstructured":"Zheng S, Song R, Wen J-R, Giles CL (2009) Efficient record-level wrapper induction. In: Proceedings of the 18th international conference on information and knowledge management (CIKM). ACM, New York, pp 47\u201356","DOI":"10.1145\/1645953.1645962"},{"issue":"4","key":"1062_CR15","doi-asserted-by":"crossref","first-page":"219","DOI":"10.14778\/1938545.1938547","volume":"4","author":"N Dalvi","year":"2011","unstructured":"Dalvi N, Kumar R, Soliman M (2011) Automatic wrappers for large scale web extraction. Proc VLDB Endow 4(4):219\u2013230","journal-title":"Proc VLDB Endow"},{"key":"1062_CR16","doi-asserted-by":"crossref","unstructured":"Buttler D, Liu L, Pu C (2001) A fully automated object extraction system for the world wide web. In: Proceedings of IEEE 21st international conference on distributed computing systems, pp 361\u2013370","DOI":"10.1109\/ICDSC.2001.918966"},{"key":"1062_CR17","doi-asserted-by":"crossref","unstructured":"Chang C, Lui S (2001) Iepad: information extraction based on pattern discovery. In: Proceedings of the 10th international conference on World Wide Web. ACM, New York, pp 681\u2013688","DOI":"10.1145\/371920.372182"},{"key":"1062_CR18","doi-asserted-by":"crossref","unstructured":"Kayed M (2012) Peer matrix alignment: a new algorithm. In: Advances in knowledge discovery and data mining, pp 268\u2013279","DOI":"10.1007\/978-3-642-30220-6_23"},{"key":"1062_CR19","doi-asserted-by":"crossref","unstructured":"Zhai Y, Liu B (2005) Web data extraction based on partial tree alignment. In: Proceedings of the 14th international conference on World Wide Web (WWW). ACM, New York, pp 76\u201385","DOI":"10.1145\/1060745.1060761"},{"key":"1062_CR20","doi-asserted-by":"crossref","unstructured":"Liu B, Zhai Y (2005) Net-a system for extracting web data from flat and nested data records. In: WISE, vol 2005. Springer, pp 487\u2013495","DOI":"10.1007\/11581062_39"},{"key":"1062_CR21","doi-asserted-by":"crossref","unstructured":"Arasu A, Garcia-Molina H (2003) Extracting structured data from web pages. In: Proceedings of ACM SIGMOD international conference on management of data, pp 337\u2013348","DOI":"10.1145\/872757.872799"},{"issue":"12","key":"1062_CR22","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1109\/TKDE.2006.197","volume":"18","author":"Y Zhai","year":"2006","unstructured":"Zhai Y, Liu B (2006) Structured data extraction from the web based on partial tree alignment. IEEE Trans Knowl Data Eng 18(12):1614\u20131628","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1062_CR23","unstructured":"Zhao H, Meng W, Yu C (2006) Automatic extraction of dynamic record sections from search engine result pages. In: Proceedings of the 32nd international conference on very large data bases, pp 989\u20131000"},{"key":"1062_CR24","doi-asserted-by":"crossref","unstructured":"Bing L, Lam W, Gu Y (2011) Towards a unified solution: Data record region detection and segmentation. In: Proceedings of the 20th ACM international conference on information and knowledge management, pp 1265\u20131274","DOI":"10.1145\/2063576.2063761"},{"key":"1062_CR25","doi-asserted-by":"crossref","unstructured":"Gatterbauer W, Bohunsky P, Herzog M, Kr\u00fcpl B, Pollak B (2007) Towards domain-independent information extraction from web tables. In: Proceedings of the 16th international conference on World Wide Web. ACM, New York, pp 71\u201380","DOI":"10.1145\/1242572.1242583"},{"key":"1062_CR26","doi-asserted-by":"crossref","unstructured":"Cai D, Yu S, Wen J-R, Ma W-Y (2003) Extracting content structure for web pages based on visual representation. In: Web technologies and applications, pp 406\u2013417","DOI":"10.1007\/3-540-36901-5_42"},{"key":"1062_CR27","doi-asserted-by":"crossref","unstructured":"Simon K, Lausen G (2005) Viper: augmenting automatic information extraction with visual perceptions. In: Proceedings of the 14th ACM international conference on information and knowledge management, pp 381\u2013388","DOI":"10.1145\/1099554.1099672"},{"issue":"4","key":"1062_CR28","doi-asserted-by":"crossref","first-page":"21:1","DOI":"10.1145\/2508434","volume":"7","author":"L Bing","year":"2013","unstructured":"Bing L, Lam W, Wong T-L (2013) Robust detection of semi-structured web records using a dom structure-knowledge-driven model. ACM Trans Web 7(4):21:1\u201321:32","journal-title":"ACM Trans Web"},{"key":"1062_CR29","doi-asserted-by":"crossref","unstructured":"Zhao H, Meng W, Wu Z, Raghavan V, Yu C (2005) Fully automatic wrapper generation for search engines. In: Proceedings of the 14th international conference on World Wide Web (WWW). ACM, New York, pp 66\u201375","DOI":"10.1145\/1060745.1060760"},{"issue":"3","key":"1062_CR30","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu W, Meng X, Meng W (2010) Vide: a vision-based approach for deep web data extraction. IEEE Trans Knowl Data Eng 22(3):447\u2013460","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1062_CR31","doi-asserted-by":"crossref","unstructured":"Fumarola F, Weninger T, Barber R, Malerba D, Han J (2011) Hylien: a hybrid approach to general list extraction on the web. In: Proceedings of the 20th international conference on World Wide Web (WWW), pp 35\u201336","DOI":"10.1145\/1963192.1963211"},{"issue":"14","key":"1062_CR32","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.14778\/2733085.2733091","volume":"7","author":"T Furche","year":"2014","unstructured":"Furche T, Gottlob G, Grasso G, Guo X, Orsi G, Schallhart C, Wang C (2014) Diadem: thousands of websites to a single database. Proc VLDB Endow 7(14):1845\u20131856","journal-title":"Proc VLDB Endow"},{"key":"1062_CR33","doi-asserted-by":"crossref","unstructured":"Crescenzi V, Merialdo P, Qiu D (2013) Alfred: crowd assisted data extraction. In: Proceedings of the 22th international conference on World Wide Web (WWW), pp 297\u2013300","DOI":"10.1145\/2487788.2487927"},{"key":"1062_CR34","doi-asserted-by":"crossref","unstructured":"Kondreddi SK, Triantafillou P, Weikum G (2014) Combining information extraction and human computing for crowdsourced knowledge acquisition. In: IEEE 30th international conference on data engineering, pp 988\u2013999","DOI":"10.1109\/ICDE.2014.6816717"},{"key":"1062_CR35","doi-asserted-by":"crossref","unstructured":"Pasternack J, Roth D (2009) Extracting article text from the web with maximum subsequence segmentation. In: Proceedings of the 18th international conference on World Wide Web (WWW), pp 971\u2013980","DOI":"10.1145\/1526709.1526840"},{"key":"1062_CR36","doi-asserted-by":"crossref","unstructured":"Weninger T, Hsu WH (2008) Text extraction from the web via text-to-tag ratio. In: 19th international workshop on database and expert systems application, pp 23\u201328","DOI":"10.1109\/DEXA.2008.12"},{"key":"1062_CR37","doi-asserted-by":"crossref","unstructured":"Weninger T, Hsu WH, Han J (2010) Cetr: content extraction via tag ratios. In: WWW, pp 971\u2013980","DOI":"10.1145\/1772690.1772789"},{"key":"1062_CR38","doi-asserted-by":"crossref","unstructured":"Sun F, Song D, Liao L (2011) Dom based content extraction via text density. In: SIGIR, pp 245\u2013254","DOI":"10.1145\/2009916.2009952"},{"key":"1062_CR39","doi-asserted-by":"crossref","unstructured":"Wu S, Liu J, Fan J (2015) Automatic web content extraction by combination of learning and grouping. In: Proceedings of the 24th international conference on World Wide Web (WWW), pp 1264\u20131274","DOI":"10.1145\/2736277.2741659"},{"issue":"1","key":"1062_CR40","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s10115-013-0687-x","volume":"42","author":"D Song","year":"2015","unstructured":"Song D, Sun F, Liao L (2015) A hybrid approach for content extraction with text density and visual importance of dom nodes. Knowl Inf Syst 42(1):75\u201396","journal-title":"Knowl Inf Syst"},{"issue":"1","key":"1062_CR41","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s00778-008-0100-7","volume":"18","author":"D-Y Chiu","year":"2009","unstructured":"Chiu D-Y, Wu Y-H, Chen A (2009) Efficient frequent sequence mining by a dynamic strategy switching algorithm. VLDB J 18(1):303\u2013327","journal-title":"VLDB J"},{"issue":"12","key":"1062_CR42","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.1587\/transinf.E94.D.2557","volume":"94\u2013D","author":"W-K Loh","year":"2011","unstructured":"Loh W-K, Ahn H (2011) A storage-efficient suffix tree construction algorithm for human genome sequences. IEICE Trans 94\u2013D(12):2557\u20132560","journal-title":"IEICE Trans"},{"key":"1062_CR43","unstructured":"Pei J, Han J, Mortazavi-Asl B, Pinto H, Chen Q, Dayal U, Hsu M-C (2001) Prefixspan: mining sequential patterns efficiently by prefix-projected pattern growth. In: ICCN, pp 215\u2013224"},{"key":"1062_CR44","unstructured":"Pei J, Han J, Mortazavi-Asl B, Wang J, Pinto H, Chen Q, Dayal U, Hsu M-C (2004) Mining sequential patterns by pattern-growth: the prefixspan approach. IEEE Trans Knowl Data Eng, vol\u00a016"},{"key":"1062_CR45","doi-asserted-by":"crossref","unstructured":"Xie X, Fang Y, Zhang Z, Li L (2012) Extracting data records from web using suffix tree. In: Proceedings of the 18th SIGKDD workshop on mining data semantics. ACM","DOI":"10.1145\/2350190.2350202"},{"key":"1062_CR46","unstructured":"Maa\u00df M (1999) Suffix trees and their applications. Ferienakademie"},{"key":"1062_CR47","unstructured":"Grossi R, Italiano GF (1993) Suffix trees and their applications in string algorithms. In: Proceedings of the 1st south American workshop on string processing, pp 57\u201376"},{"key":"1062_CR48","doi-asserted-by":"crossref","unstructured":"Zamir O, Etzioni O (1998) Web document clustering: a feasibility demonstration. In: Proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval, pp 46\u201354","DOI":"10.1145\/290941.290956"},{"key":"1062_CR49","doi-asserted-by":"crossref","unstructured":"Chim H, Deng X (2007) A new suffix tree similarity measure for document clustering. In Proceedings of the 16th international conference on World Wide Web. ACM, pp 121\u2013130","DOI":"10.1145\/1242572.1242590"},{"issue":"5","key":"1062_CR50","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1177\/0165551514541614","volume":"40","author":"Y Fang","year":"2014","unstructured":"Fang Y, Zhang H, Ye Y, Li X (2014) Detecting hot topics from twitter: a multiview approach. J Inf Sci 40(5):578\u2013593","journal-title":"J Inf Sci"},{"issue":"3","key":"1062_CR51","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/BF01206331","volume":"14","author":"E Ukkonen","year":"1995","unstructured":"Ukkonen E (1995) On-line construction of suffix trees. Algorithmica 14(3):249\u2013260","journal-title":"Algorithmica"},{"key":"1062_CR52","doi-asserted-by":"crossref","unstructured":"Farach M (1997) Optimal suffix tree construction with large alphabets. In: FOCS, pp 137\u2013143","DOI":"10.1109\/SFCS.1997.646102"},{"key":"1062_CR53","unstructured":"Greenberg RI (2003) Bounds on the number of longest common subsequences. CoRR, vol. cs.DM\/0301030. [Online]. Available: http:\/\/arxiv.org\/abs\/cs.DM\/0301030"},{"key":"1062_CR54","doi-asserted-by":"crossref","unstructured":"Knuth DE, Morris JH, Pratt VR (1977) Fast pattern matching in strings. SAIM J Comput 6(2):323\u2013350","DOI":"10.1137\/0206024"},{"key":"1062_CR55","doi-asserted-by":"crossref","unstructured":"Yamada Y, Craswell N, \u00a0Nakatoh T, Hirokawa S (2004) Testbed for information extraction from deep web. In: Proceedings of the 13th international conference on World Wide Web (WWW). ACM, New York, pp 346\u2013347","DOI":"10.1145\/1013367.1013468"},{"issue":"1","key":"1062_CR56","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/375360.375365","volume":"33","author":"G Navarro","year":"2001","unstructured":"Navarro G (2001) A guided tour to approximate string matching. ACM Comput Surv 33(1):31\u201388","journal-title":"ACM Comput Surv"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-017-1062-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1062-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1062-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T23:14:54Z","timestamp":1569280494000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-017-1062-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,9]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,5]]}},"alternative-id":["1062"],"URL":"https:\/\/doi.org\/10.1007\/s10115-017-1062-0","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,9]]}}}