{"id":"https://openalex.org/W3008556495","doi":"https://doi.org/10.1109/bigdata47090.2019.9006282","title":"Detecting Web Spam in Webgraphs with Predictive Model Analysis","display_name":"Detecting Web Spam in Webgraphs with Predictive Model Analysis","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008556495","doi":"https://doi.org/10.1109/bigdata47090.2019.9006282","mag":"3008556495"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078146729","display_name":"Naw Safrin Sattar","orcid":"https://orcid.org/0000-0002-6199-346X"},"institutions":[{"id":"https://openalex.org/I192396691","display_name":"University of New Orleans","ror":"https://ror.org/034mtvk83","country_code":"US","type":"education","lineage":["https://openalex.org/I192396691","https://openalex.org/I2799628689"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naw Safrin Sattar","raw_affiliation_strings":["University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA"],"affiliations":[{"raw_affiliation_string":"University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA","institution_ids":["https://openalex.org/I192396691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033369839","display_name":"Shaikh Arifuzzaman","orcid":"https://orcid.org/0000-0002-6893-2475"},"institutions":[{"id":"https://openalex.org/I192396691","display_name":"University of New Orleans","ror":"https://ror.org/034mtvk83","country_code":"US","type":"education","lineage":["https://openalex.org/I192396691","https://openalex.org/I2799628689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaikh Arifuzzaman","raw_affiliation_strings":["University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA"],"affiliations":[{"raw_affiliation_string":"University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA","institution_ids":["https://openalex.org/I192396691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087091309","display_name":"Minhaz F. Zibran","orcid":"https://orcid.org/0009-0004-5353-5030"},"institutions":[{"id":"https://openalex.org/I192396691","display_name":"University of New Orleans","ror":"https://ror.org/034mtvk83","country_code":"US","type":"education","lineage":["https://openalex.org/I192396691","https://openalex.org/I2799628689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhaz F. Zibran","raw_affiliation_strings":["University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA"],"affiliations":[{"raw_affiliation_string":"University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA","institution_ids":["https://openalex.org/I192396691"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055489121","display_name":"Md Mohiuddin Sakib","orcid":"https://orcid.org/0000-0003-1393-7110"},"institutions":[{"id":"https://openalex.org/I192396691","display_name":"University of New Orleans","ror":"https://ror.org/034mtvk83","country_code":"US","type":"education","lineage":["https://openalex.org/I192396691","https://openalex.org/I2799628689"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Mohiuddin Sakib","raw_affiliation_strings":["University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA"],"affiliations":[{"raw_affiliation_string":"University of New Orleans, 2000 Lakeshore Drive, New Orleans, LA, USA","institution_ids":["https://openalex.org/I192396691"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078146729"],"corresponding_institution_ids":["https://openalex.org/I192396691"],"apc_list":null,"apc_paid":null,"fwci":3.0523,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93139517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4299","last_page":"4308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8041760921478271},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6541064977645874},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6395705342292786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6101799011230469},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6022886633872986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5997401475906372},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5899941325187683},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5142833590507507},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5131166577339172},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.47865498065948486},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42994725704193115},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.34911590814590454},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.324306458234787},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.218878835439682},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1679450273513794},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12044966220855713},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.11904069781303406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041760921478271},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6541064977645874},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6395705342292786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6101799011230469},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6022886633872986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5997401475906372},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5899941325187683},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5142833590507507},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5131166577339172},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.47865498065948486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42994725704193115},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.34911590814590454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.324306458234787},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.218878835439682},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1679450273513794},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12044966220855713},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.11904069781303406},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W179179905","https://openalex.org/W273955616","https://openalex.org/W1517046895","https://openalex.org/W1529464143","https://openalex.org/W1728842521","https://openalex.org/W1967825155","https://openalex.org/W1979870225","https://openalex.org/W1988814344","https://openalex.org/W1994727615","https://openalex.org/W1999391954","https://openalex.org/W2009408190","https://openalex.org/W2020791430","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2077317318","https://openalex.org/W2082773934","https://openalex.org/W2101234009","https://openalex.org/W2101694308","https://openalex.org/W2102322109","https://openalex.org/W2110298216","https://openalex.org/W2128184786","https://openalex.org/W2130196635","https://openalex.org/W2133990480","https://openalex.org/W2136132422","https://openalex.org/W2142181701","https://openalex.org/W2142604303","https://openalex.org/W2156632103","https://openalex.org/W2169270715","https://openalex.org/W2174714397","https://openalex.org/W2230508580","https://openalex.org/W2258998514","https://openalex.org/W2369533282","https://openalex.org/W2401383085","https://openalex.org/W2487770199","https://openalex.org/W2697015949","https://openalex.org/W2778611688","https://openalex.org/W2887940528","https://openalex.org/W2916210121","https://openalex.org/W2916763019","https://openalex.org/W6607259140","https://openalex.org/W6610017368","https://openalex.org/W6631157121","https://openalex.org/W6631624008","https://openalex.org/W6637572315","https://openalex.org/W6675354045","https://openalex.org/W6680298704","https://openalex.org/W6681171286","https://openalex.org/W6685179926","https://openalex.org/W6708398869","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W4367336074","https://openalex.org/W4379620016","https://openalex.org/W2245616560","https://openalex.org/W3154045278","https://openalex.org/W3210764983","https://openalex.org/W4367335949","https://openalex.org/W4285162676","https://openalex.org/W4382052559","https://openalex.org/W3036529732","https://openalex.org/W2780266336"],"abstract_inverted_index":{"Web":[0],"spam":[1,49,222,244],"is":[2,239],"a":[3,61,128],"serious":[4],"threat":[5],"for":[6,34,60,178,196,207,233,245],"both":[7],"end-users":[8],"and":[9,36,65,91,101,123,141,144,160,201],"search":[10],"engines":[11],"(w.r.t.,":[12],"query":[13],"cost).":[14],"Webgraphs":[15],"can":[16],"be":[17],"exploited":[18],"in":[19,204],"detecting":[20,242],"spam.":[21],"In":[22,38],"the":[23,43,74,80,133,197,210,213],"past,":[24],"several":[25,56],"graph":[26,57,152,163,252],"mining":[27],"techniques":[28,110],"were":[29],"applied":[30],"to":[31,47,126],"measure":[32],"metrics":[33,58,253],"pages":[35],"hyperlinks.":[37],"this":[39],"paper,":[40],"we":[41,138],"justify":[42,66],"importance":[44],"of":[45,94,135,180,209,215,241],"webgraph":[46,248],"distinguish":[48],"websites":[50],"from":[51],"non-spam":[52],"ones":[53],"based":[54,153,157,249],"on":[55,71,79,220,250],"computed":[59],"labelled":[62],"dataset":[63,78,85,191,226,232],"(WEBSPAM-UK2007)":[64],"our":[67,136,181,187,216],"model":[68,188,237],"by":[69],"testing":[70],"uk-2014":[72,190],"dataset,":[73],"most":[75,179,208],"recently":[76],"available":[77],"same":[81],"(uk)":[82],"domain.":[83],"WEBSPAM-UK2007":[84,225],"includes":[86],"0.1":[87],"million":[88,194],"different":[89,230],"hosts":[90,195],"four":[92],"kinds":[93],"feature":[95,199],"sets:":[96],"Obvious,":[97],"Link,":[98],"Transformed":[99],"Link":[100],"Content.":[102],"We":[103,149,172,185],"use":[104,229],"five":[105],"prominent":[106],"machine":[107,182],"learning":[108,183],"(ML)":[109],"(i.e.,":[111],"Support":[112],"Vector":[113],"Machine":[114],"(SVM),":[115],"K-Nearest":[116],"Neighbor":[117],"(KNN),":[118],"Logistic":[119],"Regression,":[120],"Na\u00efve":[121],"Bayes":[122],"Random":[124],"Forest)":[125],"build":[127],"ML-based":[129],"classifier.":[130],"To":[131,212],"evaluate":[132],"performance":[134],"classifier,":[137],"compute":[139],"accuracy":[140,177,203],"F-1":[142],"score":[143],"perform":[145],"10-fold":[146],"cross":[147],"validation.":[148],"also":[150],"compare":[151],"features":[154,159],"with":[155,189,192,224],"content":[156],"textual":[158],"find":[161],"that":[162],"properties":[164],"are":[165],"similar":[166],"or":[167],"better":[168],"than":[169],"text":[170],"properties.":[171],"achieve":[173,202],"above":[174],"99%":[175],"training":[176],"models.":[184,211,235],"test":[186,231],"4.7":[193],"graph-based":[198],"sets":[200],"between":[205],"90-94%":[206],"best":[214],"knowledge,":[217],"prior":[218],"works":[219],"web":[221,243],"detection":[223],"did":[227],"not":[228],"their":[234],"Our":[236],"classifier":[238],"capable":[240],"any":[246],"input":[247],"its":[251],"features.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}