{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:32:24Z","timestamp":1763037144315},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T00:00:00Z","timestamp":1516233600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soc. Netw. Anal. Min."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s13278-017-0484-8","type":"journal-article","created":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T15:22:19Z","timestamp":1516288939000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Attribute selection for improving spam classification in online social networks: a rough set theory-based approach"],"prefix":"10.1007","volume":"8","author":[{"given":"Soumi","family":"Dutta","sequence":"first","affiliation":[]},{"given":"Sujata","family":"Ghatak","sequence":"additional","affiliation":[]},{"given":"Ratnadeep","family":"Dey","sequence":"additional","affiliation":[]},{"given":"Asit Kumar","family":"Das","sequence":"additional","affiliation":[]},{"given":"Saptarshi","family":"Ghosh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,1,18]]},"reference":[{"issue":"10\u201311","key":"484_CR1","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1016\/j.comcom.2013.04.004","volume":"36","author":"F Ahmed","year":"2013","unstructured":"Ahmed F, Abulaish M (2013) A generic statistical approach for spam detection in online social networks. Comput Commun 36(10\u201311):1120\u20131129","journal-title":"Comput Commun"},{"key":"484_CR2","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.patrec.2013.12.008","volume":"40","author":"S Bandyopadhyay","year":"2014","unstructured":"Bandyopadhyay S, Bhadra T, Mitra P, Maulik U (2014) Integration of dense subgraph finding with feature clustering for unsupervised feature selection. Pattern Recogn Lett 40:104\u2013112","journal-title":"Pattern Recogn Lett"},{"key":"484_CR3","doi-asserted-by":"crossref","unstructured":"Benevenuto F, Rodrigues T, Almeida V, Almeida J, Gonalves M (2009) Detecting spammers and content promoters in online video social networks. In: Proceedings of the annual Intl SIGIR conference, Boston, MA, USA","DOI":"10.1109\/INFCOMW.2009.5072127"},{"key":"484_CR4","unstructured":"Benevenuto F, Magno G, Rodrigues T, Almeida V (2010) Detecting spammers on Twitter. In: Proceedings of collaboration, electronic messaging, anti-abuse and spam conference (CEAS)"},{"key":"484_CR5","doi-asserted-by":"crossref","unstructured":"Caballero Y, Alvarez D, Bello R (2007) Feature selection algorithms using rough set theory. In: Proceedings of IEEE international conference on intelligent systems design and applications, pp 407\u2013411","DOI":"10.1109\/ISDA.2007.70"},{"key":"484_CR6","unstructured":"Capture-HPC. https:\/\/projects.honeynet.org\/capture-hpc\/"},{"issue":"2","key":"484_CR7","doi-asserted-by":"publisher","first-page":"9:1","DOI":"10.1145\/2089125.2089129","volume":"44","author":"G Caruana","year":"2012","unstructured":"Caruana G, Li M (2012) A survey of emerging approaches to spam filtering. ACM Comput Surv 44(2):9:1\u20139:27","journal-title":"ACM Comput Surv"},{"issue":"3","key":"484_CR8","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.patrec.2009.10.013","volume":"31","author":"Y Chen","year":"2010","unstructured":"Chen Y, Miao D, Wang R (2010) A rough set approach to feature selection based on ant colony optimization. Pattern Recogn Lett 31(3):226\u2013233","journal-title":"Pattern Recogn Lett"},{"key":"484_CR9","unstructured":"Chhabra S, Aggarwal A, Benevenuto F, Kumaraguru P (2011) Phi.sh\/SPSSlashDollaroCiaL: the phishing landscape through short URLs. In: proceedings of collaboration, electronic messaging, anti-abuse and spam conference (CEAS)"},{"key":"484_CR10","volume-title":"Pollution, bad-mouthing, and local marketing: the underground of location-based social networks","author":"H Costa","year":"2014","unstructured":"Costa H, de Campos Merschmann LH, Barth F, Benevenuto F (2014) Pollution, bad-mouthing, and local marketing: the underground of location-based social networks. Elsevier Information Sciences, Amsterdam"},{"key":"484_CR11","doi-asserted-by":"crossref","unstructured":"Costa H, Benevenuto F, de\u00a0Campos\u00a0Merschmann LH (2013) Detecting tip spam in location-based social networks. In: Proceedings of the 28th annual ACM symposium on applied computing (SAC)","DOI":"10.1145\/2480362.2480501"},{"issue":"1\u20134","key":"484_CR12","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/IDA-1997-1302","volume":"1","author":"M Dash","year":"1997","unstructured":"Dash M, Liu H (1997) Feature selection for classification. Intell Data Anal 1(1\u20134):131\u2013156","journal-title":"Intell Data Anal"},{"issue":"5","key":"484_CR13","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1002\/(SICI)1097-4571(19980415)49:5<423::AID-ASI5>3.0.CO;2-0","volume":"49","author":"JS Deogun","year":"1998","unstructured":"Deogun JS, Choubey SK, Raghavan VV, Sever H (1998) Feature selection and effective classifiers. J Am Soc Inf Sci 49(5):423\u2013434","journal-title":"J Am Soc Inf Sci"},{"key":"484_CR14","unstructured":"Fayyad UM, Irani KB (1993) Multi-interval discretization of continuous valued attributes for classification learning. In: Proceedings of international joint conference on artificial intelligence, vol 2, pp 1022\u20131027"},{"key":"484_CR15","doi-asserted-by":"crossref","unstructured":"Gao H, Hu J, Wilson C, Li Z, Chen Y, Zhao BY (2010) Detecting and characterizing social spam campaigns. In: Proceedings of ACM international conference on internet measurement (IMC)","DOI":"10.1145\/1879141.1879147"},{"issue":"4","key":"484_CR16","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1109\/TKDE.2012.35","volume":"25","author":"S Garcia","year":"2013","unstructured":"Garcia S, Luengo J, Saez JA, Lopez V, Herrera F (2013) A survey of discretization techniques: taxonomy and empirical analysis in supervised learning. IEEE Trans Knowl Data Eng 25(4):734\u2013750","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"484_CR17","unstructured":"Google Safe Browsing API. https:\/\/developers.google.com\/safe-browsing\/"},{"key":"484_CR18","doi-asserted-by":"crossref","unstructured":"Grier C, Thomas K, Paxson V, Zhang M (2010) @spam: the underground on 140 characters or less. In: Proceedings of ACM international conference on computer and communications security (CCS), pp 27\u201337","DOI":"10.1145\/1866307.1866311"},{"key":"484_CR19","unstructured":"Hall MA (1998) Correlation-based feature subset selection for machine learning. Ph.D. thesis, University of Waikato, Hamilton, New Zealand"},{"issue":"1","key":"484_CR20","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. SIGKDD Explor 11(1):10\u201318","journal-title":"SIGKDD Explor"},{"key":"484_CR21","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MIC.2007.125","volume":"11","author":"P Heymann","year":"2007","unstructured":"Heymann P, Koutrika G, Garcia-Molina H (2007) Fighting spam on social web sites: a survey of approaches and future challenges. IEEE Internet Comput 11:36\u201345","journal-title":"IEEE Internet Comput"},{"key":"484_CR22","unstructured":"Infomap - community detection. http:\/\/www.mapequation.org\/code.html"},{"issue":"9","key":"484_CR23","first-page":"61","volume":"4","author":"J Karimpour","year":"2012","unstructured":"Karimpour J, Noroozi AA, Abadi A (2012) The impact of feature selection on web spam detection. Int J Intell Syst Appl 4(9):61\u201367","journal-title":"Int J Intell Syst Appl"},{"issue":"1\u20132","key":"484_CR24","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","volume":"97","author":"R Kohavi","year":"1997","unstructured":"Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1\u20132):273\u2013324","journal-title":"Artif Intell"},{"issue":"3","key":"484_CR25","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/TDSC.2013.3","volume":"10","author":"S Lee","year":"2013","unstructured":"Lee S, Kim J (2013) WarningBird: a near real-time detection system for suspicious URLs in Twitter stream. IEEE Trans Dependable Secure Comput 10(3):183\u2013195","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"484_CR26","doi-asserted-by":"crossref","unstructured":"Lee K, Caverlee J, Webb S (2010) Uncovering social spammers: social honeypots + machine learning. In: Proceedings of ACM international conference on research and development in information retrieval (SIGIR), pp 435\u2013442","DOI":"10.1145\/1835449.1835522"},{"key":"484_CR27","unstructured":"Lee K, Eoff BD, Caverlee J (2011) Seven months with the devils: a long-term study of content polluters on Twitter. In: Proceedings of AAAI international conference on weblogs and social media (ICWSM)"},{"key":"484_CR28","unstructured":"Liu H, Setiono R (1996) A probabilistic approach to feature selection\u2014a filter solution. In: 13th international conference on machine learning, pp 319\u2013327"},{"issue":"8","key":"484_CR29","doi-asserted-by":"publisher","first-page":"2992","DOI":"10.1016\/j.eswa.2012.12.015","volume":"40","author":"J Martinez-Romo","year":"2013","unstructured":"Martinez-Romo J, Araujo L (2013) Detecting malicious tweets in trending topics using a statistical analysis of language. Expert Syst Appl 40(8):2992\u20133000","journal-title":"Expert Syst Appl"},{"issue":"3","key":"484_CR30","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/34.990133","volume":"24","author":"P Mitra","year":"2002","unstructured":"Mitra P, Murthy CA, Pal SK (2002) Unsupervised feature selection using feature similarity. IEEE Trans Pattern Anal Mach Intell 24(3):301\u2013312","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"484_CR31","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/BF01001956","volume":"11","author":"Z Pawlak","year":"1982","unstructured":"Pawlak Z (1982) Rough sets: basic notion. Int J Comput Inf Sci 11(5):344\u2013356","journal-title":"Int J Comput Inf Sci"},{"issue":"7","key":"484_CR32","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1080\/019697298125470","volume":"29","author":"Z Pawlak","year":"1998","unstructured":"Pawlak Z (1998) Rough set theory and its applications to data analysis. Cybern Syst 29(7):661\u2013688","journal-title":"Cybern Syst"},{"key":"484_CR33","first-page":"331","volume-title":"Intelligent decision support. Handbook of applications and advances of the rough set theory, theory and decision library","author":"A Skowron","year":"1992","unstructured":"Skowron A, Rauszer C (1992) The discernibility matrices and functions in information systems. In: Sowinski R (ed) Intelligent decision support. Handbook of applications and advances of the rough set theory, theory and decision library, vol 11. Kluwer Academic Publishers, Dordrecht, pp 331\u2013362"},{"key":"484_CR34","unstructured":"SURBL. http:\/\/www.surbl.org\/"},{"issue":"6","key":"484_CR35","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1016\/S0167-8655(02)00196-4","volume":"24","author":"RW Swiniarski","year":"2003","unstructured":"Swiniarski RW, Skowron A (2003) Rough set methods in feature selection and recognition. Pattern Recogn Lett 24(6):833\u2013849","journal-title":"Pattern Recogn Lett"},{"key":"484_CR36","unstructured":"The Spamhaus Project. http:\/\/www.spamhaus.org\/"},{"key":"484_CR37","doi-asserted-by":"crossref","unstructured":"Thomas K, Grier C, Ma J, Paxson V, Song D (2011) Design and evaluation of a real-time URL spam filtering service. In: Proceedings of IEEE symposium on security and privacy (2011)","DOI":"10.1109\/SP.2011.25"},{"issue":"5","key":"484_CR38","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1109\/TKDE.2010.147","volume":"23","author":"CY Tseng","year":"2011","unstructured":"Tseng CY, Sung PC, Chen MS (2011) Cosdes: a collaborative spam detection system with a novel e-mail abstraction scheme. IEEE Trans Knowl Data Eng 23(5):669\u2013682","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"484_CR39","unstructured":"Twitter API Home. https:\/\/dev.twitter.com"},{"key":"484_CR40","unstructured":"Wagner S, Wagner D (2007) Comparing clusterings\u2014an overview. Technical report 2006\u201304, Universit\u00e4t Karlsruhe (TH). http:\/\/digbib.ubka.uni-karlsruhe.de\/volltexte\/1000011477"},{"key":"484_CR41","unstructured":"Wild C, Seber G (2000) The Wilcoxon rank-sum test. In: Seber G (ed) Chance encounters: a first course in data analysis and inference. Wiley, New York"},{"key":"484_CR42","doi-asserted-by":"crossref","unstructured":"Xin G, Qiang G, Jing Z, Zheng-Chao Z (2010) An attribute reduction algorithm based on rough set, information entropy and ant colony optimization. In: Proceedings of IEEE international conference on signal processing, pp 1313\u20131317","DOI":"10.1109\/ICOSP.2010.5657142"},{"key":"484_CR43","unstructured":"Yang Y, Pedersen JO (1997) A comparative study on feature selection in text categorization. In: Proceedings of the international conference on machine learning (ICML), pp 412\u2013420"},{"issue":"1","key":"484_CR44","first-page":"1","volume":"15","author":"S Yardi","year":"2010","unstructured":"Yardi S, Romero D, Schoenebeck G, Boyd DM (2010) Detecting spam in a Twitter network. First Monday 15(1):1\u201313","journal-title":"First Monday"},{"issue":"4","key":"484_CR45","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1016\/S0360-8352(02)00131-6","volume":"43","author":"LY Zhai","year":"2002","unstructured":"Zhai LY, Khoo LP, Fok SC (2002) Feature extraction using rough set theory and genetic algorithms\u2014an application for the simplification of product quality evaluation. Comput Ind Eng 43(4):661\u2013676","journal-title":"Comput Ind Eng"},{"issue":"2","key":"484_CR46","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1166\/asl.2012.1768","volume":"5","author":"Y Zhang","year":"2012","unstructured":"Zhang Y, Wang S, Wu L (2012) Spam detection via feature selection and decision tree. Adv Sci Lett 5(2):726\u2013730","journal-title":"Adv Sci Lett"},{"key":"484_CR47","doi-asserted-by":"crossref","unstructured":"Zhang M, Yao JT (2004) A rough sets based approach to feature selection. In: Proceedings of IEEE annual meeting of the fuzzy information, pp 1313\u20131317","DOI":"10.1109\/NAFIPS.2004.1336322"}],"container-title":["Social Network Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13278-017-0484-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-017-0484-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-017-0484-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T14:22:24Z","timestamp":1570630944000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13278-017-0484-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,18]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["484"],"URL":"https:\/\/doi.org\/10.1007\/s13278-017-0484-8","relation":{},"ISSN":["1869-5450","1869-5469"],"issn-type":[{"value":"1869-5450","type":"print"},{"value":"1869-5469","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,18]]},"assertion":[{"value":"19 June 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2017","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"7"}}