{"id":"https://openalex.org/W3112324025","doi":"https://doi.org/10.1155/2020/6662166","title":"Detecting Web Spam Based on Novel Features from Web Page Source Code","display_name":"Detecting Web Spam Based on Novel Features from Web Page Source Code","publication_year":2020,"publication_date":"2020-12-17","ids":{"openalex":"https://openalex.org/W3112324025","doi":"https://doi.org/10.1155/2020/6662166","mag":"3112324025"},"language":"en","primary_location":{"id":"doi:10.1155/2020/6662166","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/6662166","pdf_url":"https://downloads.hindawi.com/journals/scn/2020/6662166.pdf","source":{"id":"https://openalex.org/S120683614","display_name":"Security and Communication Networks","issn_l":"1939-0114","issn":["1939-0114","1939-0122"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Security and Communication Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/scn/2020/6662166.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101869351","display_name":"Jiayong Liu","orcid":"https://orcid.org/0000-0003-3021-3771"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayong Liu","raw_affiliation_strings":["College of Cybersecurity, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Cybersecurity, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108481279","display_name":"Yu Su","orcid":"https://orcid.org/0000-0003-0685-2768"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Su","raw_affiliation_strings":["College of Cybersecurity, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Cybersecurity, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020150221","display_name":"Shun Lv","orcid":"https://orcid.org/0009-0001-9150-9552"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Lv","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075394107","display_name":"Cheng Huang","orcid":"https://orcid.org/0000-0002-5871-946X"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Huang","raw_affiliation_strings":["College of Cybersecurity, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5871-946X","affiliations":[{"raw_affiliation_string":"College of Cybersecurity, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075394107"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":{"value":2550,"currency":"USD","value_usd":2550},"apc_paid":{"value":2550,"currency":"USD","value_usd":2550},"fwci":1.9581,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90453474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"14"},"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":0.9993000030517578,"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":0.9991999864578247,"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":0.8973836898803711},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6836245059967041},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6567730903625488},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5988476872444153},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5463162660598755},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.5144014954566956},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.5127187967300415},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5078423619270325},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4889563322067261},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4548649191856384},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44641339778900146},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4435589909553528},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42478665709495544},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4200684130191803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3750890791416168},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3245721459388733},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3060632348060608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30093473196029663},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.29900306463241577},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.08563035726547241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8973836898803711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6836245059967041},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6567730903625488},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5988476872444153},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5463162660598755},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.5144014954566956},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.5127187967300415},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5078423619270325},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4889563322067261},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4548649191856384},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44641339778900146},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4435589909553528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42478665709495544},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4200684130191803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3750890791416168},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3245721459388733},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3060632348060608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30093473196029663},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.29900306463241577},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.08563035726547241},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2020/6662166","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/6662166","pdf_url":"https://downloads.hindawi.com/journals/scn/2020/6662166.pdf","source":{"id":"https://openalex.org/S120683614","display_name":"Security and Communication Networks","issn_l":"1939-0114","issn":["1939-0114","1939-0122"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Security and Communication Networks","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:79cfcd561d3b4c74ba7dcbb570e18634","is_oa":true,"landing_page_url":"https://doaj.org/article/79cfcd561d3b4c74ba7dcbb570e18634","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Security and Communication Networks, Vol 2020 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2020/6662166","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/6662166","pdf_url":"https://downloads.hindawi.com/journals/scn/2020/6662166.pdf","source":{"id":"https://openalex.org/S120683614","display_name":"Security and Communication Networks","issn_l":"1939-0114","issn":["1939-0114","1939-0122"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Security and Communication Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3223942099","display_name":null,"funder_award_id":"2020YFG0047","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3585260252","display_name":null,"funder_award_id":"61902265","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4016639641","display_name":null,"funder_award_id":"61902265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4489714228","display_name":null,"funder_award_id":"2020YFG0047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6101139229","display_name":null,"funder_award_id":"2020YFG0076","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8074169666","display_name":null,"funder_award_id":"2020YFG0076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112324025.pdf","grobid_xml":"https://content.openalex.org/works/W3112324025.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W109973975","https://openalex.org/W134004993","https://openalex.org/W658020064","https://openalex.org/W1614298861","https://openalex.org/W1984160751","https://openalex.org/W1991839217","https://openalex.org/W2006617902","https://openalex.org/W2038002297","https://openalex.org/W2040539519","https://openalex.org/W2079799661","https://openalex.org/W2100718462","https://openalex.org/W2101234009","https://openalex.org/W2106755564","https://openalex.org/W2129018774","https://openalex.org/W2174714397","https://openalex.org/W2181523240","https://openalex.org/W2187444093","https://openalex.org/W2271840356","https://openalex.org/W2277080772","https://openalex.org/W2293120407","https://openalex.org/W2321196735","https://openalex.org/W2369533282","https://openalex.org/W2424402128","https://openalex.org/W2749421715","https://openalex.org/W2762818192","https://openalex.org/W2769754220","https://openalex.org/W2774057992","https://openalex.org/W2805150911","https://openalex.org/W2808637952","https://openalex.org/W2899947761","https://openalex.org/W2907716455","https://openalex.org/W2911964244","https://openalex.org/W2916210121","https://openalex.org/W2938343957","https://openalex.org/W2964076046","https://openalex.org/W4253083841","https://openalex.org/W6621906925","https://openalex.org/W6675354045","https://openalex.org/W6685179926"],"related_works":["https://openalex.org/W2042562985","https://openalex.org/W183683573","https://openalex.org/W3021385460","https://openalex.org/W2139931245","https://openalex.org/W1990889981","https://openalex.org/W1566994962","https://openalex.org/W2028157995","https://openalex.org/W2477306097","https://openalex.org/W2178182010","https://openalex.org/W2362437884"],"abstract_inverted_index":{"Search":[0],"engine":[1],"is":[2,26,146],"critical":[3],"in":[4,23],"people\u2019s":[5],"daily":[6],"life":[7],"because":[8],"it":[9],"determines":[10],"the":[11,21,39,77,83,88,97,114,133,136,172],"information":[12],"quality":[13],"people":[14],"obtain":[15],"through":[16],"searching.":[17],"Fierce":[18],"competition":[19],"for":[20,59],"ranking":[22],"search":[24,33],"engines":[25],"not":[27],"conducive":[28],"to":[29,131],"both":[30],"users":[31],"and":[32,41,56,81,105,116,151,163],"engines.":[34],"Existing":[35],"research":[36],"mainly":[37],"studies":[38],"content":[40],"links":[42],"of":[43,47,54,108,129,135,161,166],"websites.":[44],"However,":[45],"none":[46],"these":[48],"techniques":[49],"focused":[50],"on":[51,113],"semantic":[52,106],"analysis":[53],"link":[55],"anchor":[57],"text":[58],"detection.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,125],"propose":[65],"a":[66,120,159,164],"web":[67,178],"spam":[68],"detection":[69],"method":[70,141],"by":[71],"extracting":[72],"novel":[73,91,143],"feature":[74,92,144],"sets":[75,93,128,145],"from":[76,96],"homepage":[78],"source":[79],"code":[80],"choosing":[82],"random":[84],"forest":[85],"(RF)":[86],"as":[87],"classifier.":[89],"The":[90,139],"are":[94],"extracted":[95],"homepage\u2019s":[98],"links,":[99],"hypertext":[100],"markup":[101],"language":[102],"(HTML)":[103],"structure,":[104],"similarity":[107],"content.":[109],"We":[110],"conduct":[111],"experiments":[112,130],"WEBSPAM-UK2007":[115],"UK-2011":[117],"dataset":[118],"using":[119],"five-fold":[121],"cross-validation":[122],"method.":[123,138],"Besides,":[124],"design":[126],"three":[127],"evaluate":[132],"performance":[134,154],"proposed":[137,140,173],"with":[142,148,158],"compared":[147],"different":[149],"indicators":[150],"has":[152],"better":[153],"than":[155],"other":[156],"methods":[157],"precision":[160],"0.929":[162],"recall":[165],"0.930.":[167],"Experiment":[168],"results":[169],"show":[170],"that":[171],"model":[174],"could":[175],"effectively":[176],"detect":[177],"spam.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}