{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T11:02:27Z","timestamp":1778065347507,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,2,9]],"date-time":"2017-02-09T00:00:00Z","timestamp":1486598400000},"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":["Pattern Anal Applic"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s10044-017-0602-2","type":"journal-article","created":{"date-parts":[[2017,2,9]],"date-time":"2017-02-09T11:00:07Z","timestamp":1486638007000},"page":"741-754","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A novel ensemble decision tree based on under-sampling and clonal selection for web spam detection"],"prefix":"10.1007","volume":"21","author":[{"given":"Xiao-Yong","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mu-Sheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jheng-Long","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-3513","authenticated-orcid":false,"given":"Pei-Chan","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng-Hui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,2,9]]},"reference":[{"key":"602_CR1","unstructured":"Gyongyi Z, Garcia-Molina H (2005) Web spam taxonomy. In: Proceedings of first international workshop on adversarial information retrieval on the web. pp 1\u201311"},{"key":"602_CR2","doi-asserted-by":"crossref","unstructured":"Silverstein C, Marais H, Henzinger M, Moricz M (1999) Analysis of a very large web search engine query log. In: Proceedings of the 22nd annual international ACM SIGIR conference on research and development on information retrieval. pp 6\u201312","DOI":"10.1145\/331403.331405"},{"key":"602_CR3","unstructured":"Joachims T, Granka L, Pan B, Hembrooke H, Gay G (2005) Accurately interpreting click through data as implicit feedback. In: Proceedings of the 28th annual international ACM SIGIR conference on research and development in information retrieval. pp 154\u2013161"},{"issue":"2","key":"602_CR4","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/2207243.2207252","volume":"13","author":"N Spirin","year":"2012","unstructured":"Spirin N, Han J (2012) Survey on web spam detection: principles and algorithms. ACM SIGKDD Explor Newsl 13(2):50\u201364","journal-title":"ACM SIGKDD Explor Newsl"},{"issue":"2","key":"602_CR5","first-page":"634","volume":"4","author":"A Chandra","year":"2014","unstructured":"Chandra A, Suaib M (2014) A survey on web spam and spam 2.0. Int J Adv Comput Res 4(2):634\u2013644","journal-title":"Int J Adv Comput Res"},{"issue":"4","key":"602_CR6","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1016\/j.patrec.2006.08.016","volume":"28","author":"MA Tahir","year":"2007","unstructured":"Tahir MA, Bouridane A, Kurugollu F (2007) Simultaneous feature selection and feature weighting using Hybrid Tabu Search\/K-nearest neighbor classifier. Pattern Recognit Lett 28(4):438\u2013446","journal-title":"Pattern Recognit Lett"},{"issue":"3\u20134","key":"602_CR7","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10044-008-0107-0","volume":"11","author":"B Bonev","year":"2008","unstructured":"Bonev B, Escolano F, Cazorla M (2008) Feature selection, mutual information, and the classification of high-dimensional patterns. Pattern Anal Appl 11(3\u20134):309\u2013319","journal-title":"Pattern Anal Appl"},{"key":"602_CR8","unstructured":"Kohavi R, Sommerfield D (1995) Feature subset selection using the wrapper method: overfitting and dynamic search space topology. In: Proceedings of the first international conference on knowledge discovery and data mining. AAAI press. pp 192\u2013197"},{"key":"602_CR9","unstructured":"Das S (2001) Filters, wrappers and a boosting-based hybrid for feature selection. In: Proceedings of the eighteenth international conference on machine learning. pp 74\u201381"},{"issue":"1","key":"602_CR10","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0893-6080(05)80010-3","volume":"5","author":"AL Blum","year":"1992","unstructured":"Blum AL, Rivest RL (1992) Training a 3-node neural network is NP-complete. Neural Netw 5(1):117\u2013127","journal-title":"Neural Netw"},{"issue":"4","key":"602_CR11","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1016\/j.asoc.2007.10.012","volume":"8","author":"S Lin","year":"2008","unstructured":"Lin S, Lee Z, Chen S, Tseng T (2008) Parameter determination of support vector machine and feature selection using simulated annealing approach. Appl Soft Comput 8(4):1505\u20131512","journal-title":"Appl Soft Comput"},{"issue":"1","key":"602_CR12","first-page":"53","volume":"2","author":"A Ahmed","year":"2005","unstructured":"Ahmed A (2005) Feature subset selection using ant colony optimization. Int J Comput Intell Appl 2(1):53\u201358","journal-title":"Int J Comput Intell Appl"},{"issue":"5","key":"602_CR13","first-page":"1","volume":"5","author":"F Ahmad","year":"2014","unstructured":"Ahmad F, Isa NAM, Hussain Z, Osman MK, Sulaiman SN (2014) A GA-based feature selection and parameter optimization of an ANN in diagnosing breast cancer. Pattern Anal Appl 5(5):1\u201310","journal-title":"Pattern Anal Appl"},{"issue":"1","key":"602_CR14","first-page":"1","volume":"1","author":"M Marinaki","year":"2015","unstructured":"Marinaki M, Marinakis Y (2015) A hybridization of clonal selection algorithm with iterated local search and variable neighborhood search for the feature selection problem. Memet Comput 1(1):1\u201321","journal-title":"Memet Comput"},{"issue":"1","key":"602_CR15","doi-asserted-by":"crossref","first-page":"799","DOI":"10.4028\/www.scientific.net\/KEM.500.799","volume":"500","author":"F Samadzadegan","year":"2012","unstructured":"Samadzadegan F, Namin SR, Rajabi MA (2012) Evaluating the potential of clonal selection optimization algorithm to hyperspectral image feature selection. Key Eng Mater 500(1):799\u2013805","journal-title":"Key Eng Mater"},{"issue":"3","key":"602_CR16","doi-asserted-by":"crossref","first-page":"5718","DOI":"10.1016\/j.eswa.2008.06.108","volume":"36","author":"S Yen","year":"2009","unstructured":"Yen S, Lee Y (2009) Cluster-based under-sampling approaches for imbalanced data distributions. Exp Syst Appl 36(3):5718\u20135727","journal-title":"Exp Syst Appl"},{"issue":"12","key":"602_CR17","doi-asserted-by":"crossref","first-page":"3358","DOI":"10.1016\/j.patcog.2007.04.009","volume":"40","author":"Y Sun","year":"2007","unstructured":"Sun Y, Kamel MS, Wong AK, Wang Y (2007) Cost-sensitive boosting for classification of imbalanced data. Pattern Recognit 40(12):3358\u20133378","journal-title":"Pattern Recognit"},{"issue":"1","key":"602_CR18","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/TNN.2006.882812","volume":"18","author":"X Hong","year":"2007","unstructured":"Hong X, Chen S, Harris CJ (2007) A kernel-based two-class classifier for imbalanced data sets. IEEE Trans Neural Netw 18(1):28\u201341","journal-title":"IEEE Trans Neural Netw"},{"key":"602_CR19","volume-title":"C4. 5: programs for machine learning","author":"JR Quinlan","year":"2014","unstructured":"Quinlan JR (2014) C4. 5: programs for machine learning. Elsevier, Amsterdam"},{"key":"602_CR20","doi-asserted-by":"crossref","unstructured":"Ntoulas A, Najork M, Manasse M, Fetterly D (2006) Detecting spam web pages through content analysis. In: Proceedings of the 15th international conference on World Wide Web. pp 89\u201392","DOI":"10.1145\/1135777.1135794"},{"key":"602_CR21","doi-asserted-by":"crossref","unstructured":"Castillo C, Donato D, Gionis A, Murdock V, Silvestri F (2007) Know your neighbors: Web spam detection using the web topology. In: Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval. pp 423\u2013430","DOI":"10.1145\/1277741.1277814"},{"key":"602_CR22","doi-asserted-by":"crossref","unstructured":"Liu Y, Gao B, Liu T, Zhang Y, Ma Z et al (2008) BrowseRank: letting web users vote for page importance. In: Proceedings of the 31st annual international ACM SIGIR conference on research and development in information retrieval. pp 451\u2013458","DOI":"10.1145\/1390334.1390412"},{"key":"602_CR23","doi-asserted-by":"crossref","unstructured":"Craswell N, Zoeter O, Taylor M, Ramsey B (2008) An experimental comparison of click position-bias models. In: Proceedings of the 2008 international conference on web search and data mining. pp 87\u201394","DOI":"10.1145\/1341531.1341545"},{"key":"602_CR24","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.neunet.2013.07.007","volume":"48","author":"F Scarselli","year":"2013","unstructured":"Scarselli F, Tsoi AC, Hagenbuchner M, Di Noi L (2013) Solving graph data issues using a layered architecture approach with applications to web spam detection. Neural Netw 48:78\u201390","journal-title":"Neural Netw"},{"issue":"12","key":"602_CR25","first-page":"928","volume":"1","author":"JS Jegadeesh","year":"2013","unstructured":"Jegadeesh JS, Jacob PL (2013) Web spam detection using fuzzy clustering. Int J Recent Innov Trends Comput Commun 1(12):928\u2013938","journal-title":"Int J Recent Innov Trends Comput Commun"},{"key":"602_CR26","unstructured":"Wei W, Xiao-Dong L, An-Lei H, Guang-Gang G (2013) Co-training based semi-supervised Web spam detection. In: Proceedings of 10th international conference on fuzzy systems and knowledge discovery. pp 789\u2013793"},{"issue":"04","key":"602_CR27","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1142\/S0219622006002258","volume":"5","author":"Q Yang","year":"2006","unstructured":"Yang Q, Wu X (2006) 10 challenging problems in data mining research. Int J Inf Technol Decis Mak 5(04):597\u2013604","journal-title":"Int J Inf Technol Decis Mak"},{"key":"602_CR28","doi-asserted-by":"crossref","DOI":"10.1002\/9781118646106","volume-title":"Imbalanced learning: foundations, algorithms, and applications","author":"H He","year":"2013","unstructured":"He H, Ma Y (2013) Imbalanced learning: foundations, algorithms, and applications. Wiley, Hoboken"},{"issue":"4","key":"602_CR29","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","volume":"42","author":"M Galar","year":"2012","unstructured":"Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern C Appl Rev 42(4):463\u2013484","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"602_CR30","unstructured":"Fan W, Stolfo SJ, Zhang J, Chan PK (1999) Adacost: misclassification cost-sensitive boosting. In: Proceedings of sixth international conference on machine learning (ICML-99), Bled, Slovenia. pp 97\u2013105"},{"issue":"1","key":"602_CR31","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TSMCA.2009.2029559","volume":"40","author":"C Seiffert","year":"2010","unstructured":"Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A (2010) RUSBoost: a hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern A Syst Hum 40(1):185\u2013197","journal-title":"IEEE Trans Syst Man Cybern A Syst Hum"},{"key":"602_CR32","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/978-3-540-39804-2_12","volume-title":"Knowledge discovery in databases: PKDD 2003","author":"NV Chawla","year":"2003","unstructured":"Chawla NV, Lazarevic A, Hall LO, Bowyer KW (2003) SMOTEBoost: improving prediction of the minority class in boosting. Knowledge discovery in databases: PKDD 2003. Springer, New York, pp 107\u2013119"},{"key":"602_CR33","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/j.neucom.2014.07.064","volume":"150","author":"J Blaszczynski","year":"2015","unstructured":"Blaszczynski J, Stefanowski J (2015) Neighbourhood sampling in bagging for imbalanced data. Neurocomputing 150:529\u2013542","journal-title":"Neurocomputing"},{"issue":"5\u20136","key":"602_CR34","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1002\/sam.10061","volume":"2","author":"S Hido","year":"2009","unstructured":"Hido S, Kashima H, Takahashi Y (2009) Roughly balanced bagging for imbalanced data. Stat Anal Data Min 2(5\u20136):412\u2013426","journal-title":"Stat Anal Data Min"},{"issue":"2","key":"602_CR35","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TSMCB.2008.2007853","volume":"39","author":"X Liu","year":"2009","unstructured":"Liu X, Wu J, Zhou Z (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern B Cybern 39(2):539\u2013550","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"602_CR36","doi-asserted-by":"crossref","unstructured":"Geng GG, Wang CH, Li QD, Xu L, Jin XB (2007) Boosting the performance of web spam detection with ensemble under-sampling classification. In: Proceedings of the IEEE fourth international conference on fuzzy systems and knowledge discovery. pp 583\u2013587","DOI":"10.1109\/FSKD.2007.207"},{"key":"602_CR37","doi-asserted-by":"crossref","unstructured":"Kira K, Rendell LA (1992) A practical approach to feature selection. In: Proceedings of the ninth international workshop on machine learning. pp 249\u2013256","DOI":"10.1016\/B978-1-55860-247-2.50037-1"},{"issue":"3","key":"602_CR38","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/TEVC.2002.1011539","volume":"6","author":"LN Castro De","year":"2002","unstructured":"De Castro LN, Von Zuben FJ (2002) Learning and optimization using the clonal selection principle. IEEE Trans Evolut Comput 6(3):239\u2013251","journal-title":"IEEE Trans Evolut Comput"},{"key":"602_CR39","unstructured":"De Castro LN, Von Zuben FJ (2002) The clonal selection algorithm with engineering applications. In: Proceedings of the 17th genetic and evolutionary computation conference. pp 36\u201337"},{"issue":"6","key":"602_CR40","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1109\/TEVC.2011.2173580","volume":"16","author":"G Dudek","year":"2012","unstructured":"Dudek G (2012) An artificial immune system for classification with local feature selection. IEEE Trans Evolut Comput 16(6):847\u2013860","journal-title":"IEEE Trans Evolut Comput"},{"issue":"2","key":"602_CR41","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/1189702.1189703","volume":"40","author":"C Castillo","year":"2006","unstructured":"Castillo C, Donato D, Becchetti L, Boldi P, Leonardi S et al (2006) A reference collection for web spam. ACM Sigir Forum 40(2):11\u201324","journal-title":"ACM Sigir Forum"},{"key":"602_CR42","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Schutze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge"},{"issue":"8","key":"602_CR43","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861\u2013874","journal-title":"Pattern Recognit Lett"},{"issue":"1","key":"602_CR44","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29\u201336","journal-title":"Radiology"},{"issue":"584","key":"602_CR45","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1256\/003590002320603584","volume":"128","author":"SJ Mason","year":"2002","unstructured":"Mason SJ, Graham NE (2002) Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: statistical significance and interpretation. Q J R Meteorol Soc 128(584):2145\u20132166","journal-title":"Q J R Meteorol Soc"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10044-017-0602-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-017-0602-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-017-0602-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,7,17]],"date-time":"2018-07-17T13:27:26Z","timestamp":1531834046000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10044-017-0602-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,9]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["602"],"URL":"https:\/\/doi.org\/10.1007\/s10044-017-0602-2","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,9]]}}}