{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T23:05:17Z","timestamp":1767913517068,"version":"3.49.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2018,2,10]],"date-time":"2018-02-10T00:00:00Z","timestamp":1518220800000},"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":["Soft Comput"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s00500-018-3066-4","type":"journal-article","created":{"date-parts":[[2018,2,10]],"date-time":"2018-02-10T10:56:18Z","timestamp":1518260178000},"page":"4177-4191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Context-sensitive and keyword density-based supervised machine learning techniques for malicious webpage detection"],"prefix":"10.1007","volume":"23","author":[{"given":"Betul","family":"Altay","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1665-5928","authenticated-orcid":false,"given":"Tansel","family":"Dokeroglu","sequence":"additional","affiliation":[]},{"given":"Ahmet","family":"Cosar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,10]]},"reference":[{"issue":"4","key":"3066_CR1","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1145\/2382438.2382441","volume":"30","author":"A Abbasi","year":"2012","unstructured":"Abbasi A, Zahedi F, Kaza S et al (2012) Detecting fake medical web sites using recursive trust labeling. ACM Trans Inf Syst (TOIS) 30(4):22","journal-title":"ACM Trans Inf Syst (TOIS)"},{"issue":"8","key":"3066_CR2","first-page":"695","volume":"11","author":"A Abraham","year":"2007","unstructured":"Abraham A, Ohsawa Y, Dote Y (2007) Web intelligence and chance discovery. Soft Comput Fusion Found Methodol Appl 11(8):695\u2013696","journal-title":"Soft Comput Fusion Found Methodol Appl"},{"key":"3066_CR3","unstructured":"Alexa. Alexa top sites. \n                    http:\/\/s3.amazonaws.com\/alexa-static\/top-1m.csv.zip"},{"key":"3066_CR4","doi-asserted-by":"crossref","unstructured":"Bannur SN, Saul LK, Savage S (2011) Judging a site by its content: learning the textual, structural, and visual features of malicious web pages. In: Proceedings of the 4th ACM workshop on security and artificial intelligence. ACM, pp 1\u201310","DOI":"10.1145\/2046684.2046686"},{"key":"3066_CR5","doi-asserted-by":"crossref","unstructured":"Basnet R, Mukkamala S, Sung AH (2008) Detection of phishing attacks: a machine learning approach. In: Soft computing applications in industry. Springer, pp 373\u2013383","DOI":"10.1007\/978-3-540-77465-5_19"},{"issue":"1","key":"3066_CR6","first-page":"39","volume":"22","author":"AL Berger","year":"1996","unstructured":"Berger AL, Pietra VJD, Pietra SAD (1996) A maximum entropy approach to natural language processing. Comput Linguist 22(1):39\u201371","journal-title":"Comput Linguist"},{"key":"3066_CR7","doi-asserted-by":"crossref","unstructured":"Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on computational learning theory. ACM, p 144\u2013152","DOI":"10.1145\/130385.130401"},{"key":"3066_CR8","doi-asserted-by":"crossref","unstructured":"Canali D, Cova M, Vigna G, Kruegel C (2011) Prophiler: a fast filter for the large-scale detection of malicious web pages. In: Proceedings of the 20th international conference on world wide web. ACM, pp 197\u2013206","DOI":"10.1145\/1963405.1963436"},{"issue":"1","key":"3066_CR9","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s00500-011-0740-1","volume":"16","author":"RA Carrasco","year":"2012","unstructured":"Carrasco RA, Villar P (2012) A new model for linguistic summarization of heterogeneous data: an application to tourism web data sources. Soft Comput 16(1):135\u2013151","journal-title":"Soft Comput"},{"key":"3066_CR10","unstructured":"Cdric Champeau (2014) Jlangdetect. \n                    https:\/\/github.com\/melix\/jlangdetect"},{"key":"3066_CR11","unstructured":"Chang CC, Lin CJ (2015) LIBSVM\u2014a library for support vector machines. \n                    https:\/\/www.csie.ntu.edu.tw\/~cjlin\/ libsvm\/"},{"issue":"2","key":"3066_CR12","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.dss.2007.06.002","volume":"44","author":"M Chau","year":"2008","unstructured":"Chau M, Chen H (2008) A machine learning approach to web page filtering using content and structure analysis. Decis Support Syst 44(2):482\u2013494","journal-title":"Decis Support Syst"},{"key":"3066_CR13","doi-asserted-by":"crossref","unstructured":"Chen J, Guo C (2006) Online detection and prevention of phishing attacks. In: Communications and networking in China, 2006. ChinaCom\u201906. First international conference on IEEE, pp 1\u20137","DOI":"10.1109\/CHINACOM.2006.344718"},{"key":"3066_CR14","first-page":"786","volume":"2002","author":"HL Chieu","year":"2002","unstructured":"Chieu HL, Ng HT (2002) A maximum entropy approach to information extraction from semi-structured and free text. AAAI\/IAAI 2002:786\u2013791","journal-title":"AAAI\/IAAI"},{"issue":"4","key":"3066_CR15","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1145\/1013886.1007518","volume":"29","author":"M Christodorescu","year":"2004","unstructured":"Christodorescu M, Jha S (2004) Testing malware detectors. ACM SIGSOFT Softw Eng Notes 29(4):34\u201344","journal-title":"ACM SIGSOFT Softw Eng Notes"},{"key":"3066_CR16","unstructured":"Comodo Group (2017) Creating trust online. \n                    https:\/\/www.comodo.com\/"},{"issue":"3","key":"3066_CR17","first-page":"273","volume":"20","author":"C Corinna","year":"1995","unstructured":"Corinna C, Vladimir V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"3066_CR18","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.neucom.2017.02.033","volume":"241","author":"A Deniz","year":"2017","unstructured":"Deniz A, Kiziloz HE, Dokeroglu T, Cosar A (2017) Robust multiobjective evolutionary feature subset selection algorithm for binary classification using machine learning techniques. Neurocomputing 241:128\u2013146","journal-title":"Neurocomputing"},{"issue":"1","key":"3066_CR19","first-page":"157","volume":"15","author":"A El-Halees","year":"2007","unstructured":"El-Halees A (2007) Arabic text classification using maximum entropy. Islam Univ J (Series of Natural Studies and Engineering) 15(1):157\u2013167","journal-title":"Islam Univ J (Series of Natural Studies and Engineering)"},{"key":"3066_CR20","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) Liblinear: a library for large linear classification. J Mach Learn Res 9:1871\u20131874","journal-title":"J Mach Learn Res"},{"issue":"1","key":"3066_CR21","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.eswa.2009.05.023","volume":"37","author":"Y-T Hou","year":"2010","unstructured":"Hou Y-T, Chang Y, Chen T, Laih C-S, Chen C-M (2010) Malicious web content detection by machine learning. Exp Syst Appl 37(1):55\u201360","journal-title":"Exp Syst Appl"},{"key":"3066_CR22","unstructured":"Hsu CW, Chang CC, Lin et al (2003) A practical guide to support vector classification"},{"key":"3066_CR23","unstructured":"Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: Neural networks, 2004. Proceedings. 2004 IEEE international joint conference on IEEE, vol 2, pp 985\u2013990"},{"issue":"1","key":"3066_CR24","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"G-B Huang","year":"2006","unstructured":"Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489\u2013501","journal-title":"Neurocomputing"},{"issue":"2","key":"3066_CR25","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s13042-011-0019-y","volume":"2","author":"GB Huang","year":"2011","unstructured":"Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107\u2013122","journal-title":"Int J Mach Learn Cybern"},{"key":"3066_CR26","unstructured":"International\u00a0Telecommunication Union (2015) Statistics. \n                    http:\/\/www.itu.int\/en\/ITU-D\/Statistics\/Documents\/statistics\/2015\/ITU_Key_2005-2015_ICT_data.xls"},{"key":"3066_CR27","doi-asserted-by":"crossref","unstructured":"Invernizzi L, Comparetti PM, Benvenuti S, Kruegel C, Cova M, Vigna G (2012) Evilseed: a guided approach to finding malicious web pages. In: Security and privacy (SP), 2012 IEEE symposium on IEEE, pp 428\u2013442","DOI":"10.1109\/SP.2012.33"},{"issue":"3","key":"3066_CR28","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1016\/j.eswa.2014.08.046","volume":"42","author":"HB Kazemian","year":"2015","unstructured":"Kazemian HB, Ahmed S (2015) Comparisons of machine learning techniques for detecting malicious webpages. Exp Syst Appl 42(3):1166\u20131177","journal-title":"Exp Syst Appl"},{"key":"3066_CR29","unstructured":"Machine Learning\u00a0Group at\u00a0National Taiwan\u00a0University (2015) Liblinear\u2014a library for large linear classification. \n                    https:\/\/www.csie.ntu.edu.tw\/~cjlin\/liblinear\/"},{"key":"3066_CR30","unstructured":"Moshchuk A, Bragin T, Damien D, Gribble SD, Levy HM (2007) Execution-based detection of malicious web content. In: USENIX security, Spyproxy"},{"key":"3066_CR31","unstructured":"Nigam K, Lafferty J, McCallum A (1999) Using maximum entropy for text classification. In: IJCAI-99 workshop on machine learning for information filtering, vol 1, pp 61\u201367"},{"issue":"151","key":"3066_CR32","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1090\/S0025-5718-1980-0572855-7","volume":"35","author":"J Nocedal","year":"1980","unstructured":"Nocedal J (1980) Updating quasi-newton matrices with limited storage. Math Comput 35(151):773\u2013782","journal-title":"Math Comput"},{"key":"3066_CR33","unstructured":"Pang B, Lee L, Vaithyanathan S (2002) Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the ACL-02 conference on Empirical methods in natural language processing, vol 10. Association for Computational Linguistics, pp 79\u201386"},{"key":"3066_CR34","unstructured":"PhishTank P (2016) Join the fight against phishing. \n                    https:\/\/www.phishtank.com\/developer_info.php"},{"key":"3066_CR35","doi-asserted-by":"crossref","unstructured":"Prakash P, Kumar M, Kompella RR, Gupta M (2010) Phishnet: predictive blacklisting to detect phishing attacks. In: INFOCOM, 2010 proceedings IEEE. IEEE, pp. 1\u20135","DOI":"10.1109\/INFCOM.2010.5462216"},{"key":"3066_CR36","first-page":"4","volume":"7","author":"N Provos","year":"2007","unstructured":"Provos N, McNamee D, Mavrommatis P, Wang K, Modadugu N et al (2007) The ghost in the browser: analysis of web-based malware. HotBots 7:4\u20134","journal-title":"HotBots"},{"key":"3066_CR37","doi-asserted-by":"crossref","unstructured":"Seifert C, Welch I, Komisarczuk P (2008) Identification of malicious web pages with static heuristics. In: Telecommunication networks and applications conference, 2008. ATNAC 2008. Australasian. IEEE, pp 91\u201396","DOI":"10.1109\/ATNAC.2008.4783302"},{"key":"3066_CR38","doi-asserted-by":"crossref","unstructured":"Seifert C, Welch I, Komisarczuk P, Aval CU, Endicott-Popovsky B (2008) Identification of malicious web pages through analysis of underlying DNS and web server relationships. In: LCN, Citeseer, pp 935\u2013941","DOI":"10.1109\/LCN.2008.4664306"},{"key":"3066_CR39","doi-asserted-by":"crossref","unstructured":"Sirageldin A, Baharudin BB, Jung LT (2014) Malicious web page detection: a machine learning approach. In: Advances in computer science and its applications. Springer, pp 217\u2013224","DOI":"10.1007\/978-3-642-41674-3_32"},{"key":"3066_CR40","unstructured":"Tsuruoka Y (2006) A simple c++ library for maximum entropy classification v3.0. Software available at \n                    http:\/\/www.nactem.ac.uk\/tsuruoka\/maxent\/"},{"key":"3066_CR41","doi-asserted-by":"crossref","unstructured":"Tsuruoka Y, Tsujii J, Ananiadou S (2009) Stochastic gradient descent training for l1-regularized log-linear models with cumulative penalty. In: Proceedings of the joint conference of the 47th annual meeting of the ACL and the 4th international joint conference on natural language processing of the AFNLP, volume 1\u20131. Association for computational linguistics, pp 477\u2013485","DOI":"10.3115\/1687878.1687946"},{"key":"3066_CR42","doi-asserted-by":"crossref","unstructured":"Wassermann G, Su Z (2008) Static detection of cross-site scripting vulnerabilities. In: 2008 ACM\/IEEE 30th international conference on software engineering. IEEE, pp 171\u2013180","DOI":"10.1145\/1368088.1368112"},{"key":"3066_CR43","unstructured":"Zhu QY, Huang GB (2004) Basic ELM algorithms. \n                    http:\/\/www.ntu.edu.sg\/home\/egbhuang\/elm_codes.html"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-018-3066-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-018-3066-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-018-3066-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,6]],"date-time":"2019-05-06T09:03:51Z","timestamp":1557133431000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-018-3066-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,10]]},"references-count":43,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["3066"],"URL":"https:\/\/doi.org\/10.1007\/s00500-018-3066-4","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,10]]},"assertion":[{"value":"10 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"There is no conflict of interest between authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This article does not contain any studies with human participants performed by any of the authors. This article does not contain any studies with animals performed by any of the authors. This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical standard"}},{"value":"There is no individual participant included in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}