{"id":"https://openalex.org/W90847830","doi":"https://doi.org/10.1155/2021/6625739","title":"An Improved Framework for Content\u2010 and Link\u2010Based Web\u2010Spam Detection: A Combined Approach","display_name":"An Improved Framework for Content\u2010 and Link\u2010Based Web\u2010Spam Detection: A Combined Approach","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W90847830","doi":"https://doi.org/10.1155/2021/6625739","mag":"90847830"},"language":"en","primary_location":{"id":"doi:10.1155/2021/6625739","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6625739","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6625739.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"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":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2021/6625739.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077964472","display_name":"Asim Shahzad","orcid":"https://orcid.org/0000-0001-5650-3983"},"institutions":[{"id":"https://openalex.org/I3131573596","display_name":"Abbottabad University of Science and Technology","ror":"https://ror.org/0549hdw45","country_code":"PK","type":"education","lineage":["https://openalex.org/I3131573596"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Asim Shahzad","raw_affiliation_strings":["Faculty of Computer Science, Abbottabad University of Science and Technology, KPK, Abbottabad, Pakistan"],"raw_orcid":"https://orcid.org/0000-0001-5650-3983","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Abbottabad University of Science and Technology, KPK, Abbottabad, Pakistan","institution_ids":["https://openalex.org/I3131573596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006730304","display_name":"Nazri Mohd Nawi","orcid":"https://orcid.org/0000-0003-0685-7892"},"institutions":[{"id":"https://openalex.org/I930072361","display_name":"Tun Hussein Onn University of Malaysia","ror":"https://ror.org/01c5wha71","country_code":"MY","type":"education","lineage":["https://openalex.org/I930072361"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Nazri Mohd Nawi","raw_affiliation_strings":["Soft Computing & Data Mining Centre (SMC), Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor 86400, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-0685-7892","affiliations":[{"raw_affiliation_string":"Soft Computing & Data Mining Centre (SMC), Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor 86400, Malaysia","institution_ids":["https://openalex.org/I930072361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091046843","display_name":"Muhammad Zubair Rehman","orcid":"https://orcid.org/0000-0003-2589-4189"},"institutions":[{"id":"https://openalex.org/I45998257","display_name":"Sohar University","ror":"https://ror.org/02ftvf862","country_code":"OM","type":"education","lineage":["https://openalex.org/I45998257"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Muhammad Zubair Rehman","raw_affiliation_strings":["Faculty of Computing and IT, Sohar University, Sohar 311, Oman"],"raw_orcid":"https://orcid.org/0000-0003-2589-4189","affiliations":[{"raw_affiliation_string":"Faculty of Computing and IT, Sohar University, Sohar 311, Oman","institution_ids":["https://openalex.org/I45998257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013621949","display_name":"Abdullah Khan","orcid":"https://orcid.org/0000-0003-1718-7038"},"institutions":[{"id":"https://openalex.org/I246743127","display_name":"The University of Agriculture, Peshawar","ror":"https://ror.org/02sp3q482","country_code":"PK","type":"education","lineage":["https://openalex.org/I246743127"]},{"id":"https://openalex.org/I4210127363","display_name":"Institute of Management Sciences Peshawar","ror":"https://ror.org/02m8e1r74","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210127363"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Abdullah Khan","raw_affiliation_strings":["Institute of Computer Sciences and Information Technology, Faculty of Management and Computer Sciences, University of Agriculture, Peshawar, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-1718-7038","affiliations":[{"raw_affiliation_string":"Institute of Computer Sciences and Information Technology, Faculty of Management and Computer Sciences, University of Agriculture, Peshawar, Pakistan","institution_ids":["https://openalex.org/I4210127363","https://openalex.org/I246743127"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013621949"],"corresponding_institution_ids":["https://openalex.org/I246743127","https://openalex.org/I4210127363"],"apc_list":{"value":2300,"currency":"USD","value_usd":2300},"apc_paid":{"value":2300,"currency":"USD","value_usd":2300},"fwci":1.3845,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84225186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"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":0.9988999962806702,"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":0.9984999895095825,"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/spamming","display_name":"Spamming","score":0.8686985969543457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695544958114624},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.7120898962020874},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7061967253684998},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6268048286437988},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.4999823570251465},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.48534074425697327},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4539605379104614},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.44688481092453003},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.44657203555107117},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.4357251822948456},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.413621723651886},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.41121432185173035},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.4100298583507538},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.3266807794570923},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2873190641403198}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.8686985969543457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695544958114624},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.7120898962020874},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7061967253684998},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6268048286437988},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.4999823570251465},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.48534074425697327},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4539605379104614},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.44688481092453003},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.44657203555107117},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.4357251822948456},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.413621723651886},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.41121432185173035},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.4100298583507538},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.3266807794570923},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2873190641403198}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1155/2021/6625739","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6625739","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6625739.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"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":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:eprints.uthm.edu.my:1777","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.uthm.edu.my/1777/1/ASIM%20SHAHZAD%20-%2024p.pdf","source":{"id":"https://openalex.org/S4306400770","display_name":"UTHM Institutional Repository (Universiti Tun Hussein Onn Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I930072361","host_organization_name":"Tun Hussein Onn University of Malaysia","host_organization_lineage":["https://openalex.org/I930072361"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"pmh:oai:RePEc:hin:complx:6625739","is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/complexity/2021/6625739.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:274c41712f3d4001b9f65cdbbcac9d18","is_oa":true,"landing_page_url":"https://doaj.org/article/274c41712f3d4001b9f65cdbbcac9d18","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":"Complexity, Vol 2021 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2021/6625739","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6625739","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6625739.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"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":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310112","display_name":"Universiti Tun Hussein Onn Malaysia","ror":"https://ror.org/01c5wha71"},{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W90847830.pdf","grobid_xml":"https://content.openalex.org/works/W90847830.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1614703486","https://openalex.org/W1880262756","https://openalex.org/W1967825155","https://openalex.org/W1984160751","https://openalex.org/W1985683032","https://openalex.org/W1987365175","https://openalex.org/W2012286502","https://openalex.org/W2027116318","https://openalex.org/W2049541992","https://openalex.org/W2050028965","https://openalex.org/W2066055909","https://openalex.org/W2079672501","https://openalex.org/W2079799661","https://openalex.org/W2085030399","https://openalex.org/W2091846785","https://openalex.org/W2100738695","https://openalex.org/W2103456180","https://openalex.org/W2106444274","https://openalex.org/W2114365847","https://openalex.org/W2117138276","https://openalex.org/W2128184786","https://openalex.org/W2128272588","https://openalex.org/W2139532006","https://openalex.org/W2152565070","https://openalex.org/W2165612380","https://openalex.org/W2165613200","https://openalex.org/W2293120407","https://openalex.org/W2401383085","https://openalex.org/W2758317362","https://openalex.org/W2774057992","https://openalex.org/W2810805844","https://openalex.org/W2889350921","https://openalex.org/W2898023554","https://openalex.org/W2964491004","https://openalex.org/W3005122420","https://openalex.org/W4211088835","https://openalex.org/W4237791300","https://openalex.org/W4248064238","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W2080521416","https://openalex.org/W2091208042","https://openalex.org/W2018000323","https://openalex.org/W2920666515","https://openalex.org/W2738482239","https://openalex.org/W2246912952","https://openalex.org/W2552201931","https://openalex.org/W1551975479","https://openalex.org/W3098355271","https://openalex.org/W2100081831"],"abstract_inverted_index":{"In":[0],"this":[1],"modern":[2],"era,":[3],"people":[4],"utilise":[5],"the":[6,46,57,80,104,126,130,155,208,212,219,233,269,274],"web":[7,41,69,83,96,101,118,132,152,214],"to":[8,12,33,78,169,240,250],"share":[9],"information":[10,18,124],"and":[11,15,29,38,138,176,194,216,226,235,249,255,271],"deliver":[13],"services":[14],"products.":[16],"The":[17,180],"seekers":[19],"use":[20],"different":[21,111],"search":[22,34,105],"engines":[23],"(SEs)":[24],"such":[25],"as":[26,31],"Google,":[27],"Bing,":[28],"Yahoo":[30],"tools":[32],"for":[35,125,174,197],"products,":[36],"services,":[37],"information.":[39],"However,":[40],"spamming":[42,215],"is":[43,66,146,166],"one":[44],"of":[45,59,82,148,187,244,263,273],"most":[47],"significant":[48],"issues":[49],"encountered":[50],"by":[51],"SEs":[52,77],"because":[53,68],"it":[54],"dramatically":[55],"affects":[56],"quality":[58],"SE":[60,92],"results.":[61],"Web":[62,158],"spamming\u2019s":[63],"economic":[64],"impact":[65],"enormous":[67],"spammers":[70],"index":[71],"massive":[72],"free":[73],"advertising":[74],"data":[75],"on":[76,85,154],"increase":[79],"volume":[81],"traffic":[84],"a":[86],"targeted":[87],"website.":[88],"Spammers":[89],"trick":[90],"an":[91,167,171],"into":[93],"ranking":[94],"irrelevant":[95],"pages":[97,102,108,119,153],"higher":[98],"than":[99],"relevant":[100],"in":[103],"engine":[106],"results":[107],"(SERPs)":[109],"using":[110],"web\u2010spamming":[112],"techniques.":[113],"Consequently,":[114],"these":[115],"high\u2010ranked":[116],"unrelated":[117],"contain":[120],"insufficient":[121],"or":[122],"inappropriate":[123],"user.":[127],"To":[128,246],"detect":[129],"spam":[131,151,191,224,237],"pages,":[133,223],"several":[134],"researchers":[135],"from":[136],"industry":[137],"academia":[139],"are":[140],"working.":[141],"No":[142],"efficient":[143],"technique":[144],"that":[145],"capable":[147],"catching":[149],"all":[150,232],"World":[156],"Wide":[157],"(WWW)":[159],"has":[160],"been":[161],"presented":[162],"yet.":[163],"This":[164],"research":[165],"attempt":[168],"propose":[170],"improved":[172],"framework":[173,181],"content\u2010":[175,234],"link\u2010based":[177,202,213,236],"web\u2010spam":[178,199,203],"identification.":[179],"uses":[182],"stopwords,":[183],"keywords\u2019":[184],"frequency,":[185],"part":[186],"speech":[188],"(POS)":[189],"ratio,":[190],"keywords":[192],"database,":[193,221],"copied\u2010content":[195],"algorithms":[196,239],"content\u2010based":[198],"detection.":[200],"For":[201],"detection,":[204],"we":[205,230],"initially":[206],"exposed":[207],"relationship":[209],"network":[210],"behind":[211],"then":[217],"used":[218],"paid\u2010link":[220],"neighbour":[222],"signals,":[225],"link\u2010farm":[227],"algorithms.":[228],"Finally,":[229],"combined":[231],"identification":[238],"identify":[241],"both":[242],"types":[243],"spam.":[245],"conduct":[247],"experiments":[248],"obtain":[251],"threshold":[252],"values,":[253],"WEBSPAM\u2010UK2006":[254],"WEBSPAM\u2010UK2007":[256],"datasets":[257],"were":[258],"used.":[259],"A":[260],"promising":[261],"F\u2010measure":[262],"79.6%":[264],"with":[265],"81.2%":[266],"precision":[267],"shows":[268],"applicability":[270],"effectiveness":[272],"proposed":[275],"approach.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}
