{"id":"https://openalex.org/W7138944059","doi":"https://doi.org/10.1109/icacs69208.2026.11433158","title":"Identifying Website Applications Through Zero-Content URL Classification","display_name":"Identifying Website Applications Through Zero-Content URL Classification","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7138944059","doi":"https://doi.org/10.1109/icacs69208.2026.11433158"},"language":null,"primary_location":{"id":"doi:10.1109/icacs69208.2026.11433158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacs69208.2026.11433158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 7th International Conference on Advancements in Computational Sciences (ICACS)","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/A5130055276","display_name":"Muhammad Aleem Siddique Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Muhammad Aleem Siddique Khan","raw_affiliation_strings":["NUST, SEECS,Faculty of Computing,Islamabad,Pakistan"],"affiliations":[{"raw_affiliation_string":"NUST, SEECS,Faculty of Computing,Islamabad,Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130191233","display_name":"Addul Basit","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Addul Basit","raw_affiliation_strings":["NUST, SEECS,Faculty of Computing,Islamabad,Pakistan"],"affiliations":[{"raw_affiliation_string":"NUST, SEECS,Faculty of Computing,Islamabad,Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125708207","display_name":"Ahmad Raza","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ahmad Raza","raw_affiliation_strings":["Sungkyunkwan University,Applied Artificial Intelligence,Suwon,South Korea"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Applied Artificial Intelligence,Suwon,South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122847013","display_name":"Muhammad Zeeshan","orcid":null},"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 Zeeshan","raw_affiliation_strings":["Sohar University,Computing and Technology,Sohar,Oman"],"affiliations":[{"raw_affiliation_string":"Sohar University,Computing and Technology,Sohar,Oman","institution_ids":["https://openalex.org/I45998257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070064684","display_name":"Muzamil Ahmad Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muzamil Khan","raw_affiliation_strings":["NUST, SEECS,Faculty of Computing,Islamabad,Pakistan"],"affiliations":[{"raw_affiliation_string":"NUST, SEECS,Faculty of Computing,Islamabad,Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130049556","display_name":"Ansar","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ansar","raw_affiliation_strings":["University of Engineering and Technology,Electrical Engineering Department,Lahore,Pakistan"],"affiliations":[{"raw_affiliation_string":"University of Engineering and Technology,Electrical Engineering Department,Lahore,Pakistan","institution_ids":["https://openalex.org/I142732210"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5130055276"],"corresponding_institution_ids":["https://openalex.org/I929597975"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93508903,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.4691999852657318,"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":0.4691999852657318,"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":0.3068000078201294,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.05009999871253967,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5246000289916992},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5052000284194946},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.49799999594688416},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4381999969482422},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.3668999969959259},{"id":"https://openalex.org/keywords/headline","display_name":"Headline","score":0.3635999858379364},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3594000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825999855995178},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icacs69208.2026.11433158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacs69208.2026.11433158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 7th International Conference on Advancements in Computational Sciences (ICACS)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Approximately":[0],"1.13":[1],"billion":[2],"websites":[3,34],"span":[4],"diverse":[5],"domains":[6],"like":[7],"music,":[8],"movies,":[9],"health,":[10],"video":[11],"games,":[12],"social":[13],"media,":[14],"entertainment,":[15],"and":[16,89,104,127,132,142],"more,":[17],"making":[18],"website":[19],"classification":[20],"highly":[21,73],"valuable":[22],"yet":[23],"challenging.":[24],"This":[25],"research":[26,50],"explores":[27],"using":[28,92,156],"Artificial":[29],"Intelligence":[30],"techniques":[31,134],"to":[32,145],"categorize":[33],"into":[35,61],"appropriate":[36],"classes.":[37],"The":[38],"DMOZ":[39],"dataset":[40],"is":[41,72],"one":[42],"of":[43,67,164],"the":[44,65,152,157],"most":[45,153],"reliable":[46],"data":[47,130],"sources":[48],"for":[49,140],"focused":[51],"on":[52,110],"URLs,":[53],"containing":[54],"about":[55],"1.5":[56],"million":[57],"URLs":[58,68,82,147],"manually":[59],"classified":[60,90],"different":[62,70],"categories,":[63],"though":[64],"distribution":[66],"across":[69],"categories":[71],"unbalanced.":[74],"To":[75],"overcome":[76],"this":[77],"limitation,":[78],"we":[79],"collected":[80],"500,000":[81],"from":[83],"DomCop's":[84],"Top":[85],"10":[86],"Million":[87],"Websites":[88],"them":[91],"Large":[93],"Language":[94],"Models":[95],"(LLMs),":[96],"specifically":[97],"LLaMA":[98],"3":[99],"3B.":[100],"Numerous":[101],"machine":[102],"learning":[103,106],"deep":[105],"models":[107],"were":[108,135],"trained":[109],"both":[111],"datasets,":[112],"including":[113,138],"logistic":[114],"regression,":[115],"support":[116],"vector":[117],"machine,":[118],"decision":[119],"trees,":[120],"random":[121],"forest,":[122],"CatBoost,":[123],"XgBoost,":[124],"LSTM,":[125],"Bi-LSTM,":[126],"FastText.":[128],"Different":[129],"handling":[131],"pre-processing":[133],"also":[136],"employed,":[137],"chunking":[139],"balancing":[141],"subdomain":[143],"extraction":[144],"increase":[146],"per":[148],"category.":[149],"We":[150],"report":[151],"successful":[154],"pipeline":[155],"FastText":[158],"model,":[159],"achieving":[160],"an":[161],"average":[162],"accuracy":[163],"82%.":[165]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}