{"id":"https://openalex.org/W4361793676","doi":"https://doi.org/10.1145/3582197.3582206","title":"An Experimental Approach for Hybrid Content-based Web Page Detection","display_name":"An Experimental Approach for Hybrid Content-based Web Page Detection","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4361793676","doi":"https://doi.org/10.1145/3582197.3582206"},"language":"en","primary_location":{"id":"doi:10.1145/3582197.3582206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582197.3582206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 10th International Conference on Information Technology: IoT and Smart City","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/A5084616162","display_name":"Ken Gorro","orcid":"https://orcid.org/0000-0001-5423-373X"},"institutions":[{"id":"https://openalex.org/I3131611854","display_name":"Cebu Institute of Technology University","ror":"https://ror.org/02a6jmr02","country_code":"PH","type":"education","lineage":["https://openalex.org/I3131611854"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"Ken Gorro","raw_affiliation_strings":["Cebu Institute of Technology University, Philippines"],"affiliations":[{"raw_affiliation_string":"Cebu Institute of Technology University, Philippines","institution_ids":["https://openalex.org/I3131611854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063510066","display_name":"Larmie S. Feliscuzo","orcid":"https://orcid.org/0000-0001-8155-3843"},"institutions":[{"id":"https://openalex.org/I3131611854","display_name":"Cebu Institute of Technology University","ror":"https://ror.org/02a6jmr02","country_code":"PH","type":"education","lineage":["https://openalex.org/I3131611854"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Larmie Feliscuzo","raw_affiliation_strings":["Cebu Institute of Technology University, Philippines"],"affiliations":[{"raw_affiliation_string":"Cebu Institute of Technology University, Philippines","institution_ids":["https://openalex.org/I3131611854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020964578","display_name":"Cherry Lyn C. Sta. Romana","orcid":"https://orcid.org/0000-0002-4201-3315"},"institutions":[{"id":"https://openalex.org/I3131611854","display_name":"Cebu Institute of Technology University","ror":"https://ror.org/02a6jmr02","country_code":"PH","type":"education","lineage":["https://openalex.org/I3131611854"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Cherry Lyn Sta. Romana","raw_affiliation_strings":["Cebu Institute of Technology University, Philippines"],"affiliations":[{"raw_affiliation_string":"Cebu Institute of Technology University, Philippines","institution_ids":["https://openalex.org/I3131611854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084616162"],"corresponding_institution_ids":["https://openalex.org/I3131611854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19140037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.998199999332428,"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":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199237585067749},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7067645192146301},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.7027942538261414},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6989227533340454},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.698858380317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6696842908859253},{"id":"https://openalex.org/keywords/javascript","display_name":"JavaScript","score":0.6021196246147156},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5878897309303284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3948037326335907},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3589264750480652},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2245238721370697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199237585067749},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7067645192146301},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.7027942538261414},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6989227533340454},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.698858380317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696842908859253},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.6021196246147156},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5878897309303284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3948037326335907},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3589264750480652},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2245238721370697},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582197.3582206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582197.3582206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 10th International Conference on Information Technology: IoT and Smart City","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1147066959","https://openalex.org/W1620768084","https://openalex.org/W1985920648","https://openalex.org/W2011332048","https://openalex.org/W2127744755","https://openalex.org/W2160353917","https://openalex.org/W2167912153","https://openalex.org/W2282784985","https://openalex.org/W2462859981","https://openalex.org/W2560838595","https://openalex.org/W2567869469","https://openalex.org/W2617978315","https://openalex.org/W2734726005","https://openalex.org/W2741026990","https://openalex.org/W2766389674","https://openalex.org/W2800391419","https://openalex.org/W3043102860","https://openalex.org/W4236296534","https://openalex.org/W4289812585","https://openalex.org/W4310969338"],"related_works":["https://openalex.org/W47352601","https://openalex.org/W2981957539","https://openalex.org/W4287378204","https://openalex.org/W2545422590","https://openalex.org/W4240705470","https://openalex.org/W2945311252","https://openalex.org/W631546281","https://openalex.org/W4206501676","https://openalex.org/W88292646","https://openalex.org/W2914791830"],"abstract_inverted_index":{"Almost":[0],"everyone":[1],"is":[2,46,114,126,138],"using":[3,32,98,150],"the":[4,23,39,43,105,112,132],"internet":[5],"that":[6,67,143],"includes":[7],"children":[8],"from":[9],"5":[10,117],"years":[11,15],"old":[12],"to":[13,22,42,49,108,116,177,213,217],"18":[14],"old.":[16],"Pornographic":[17],"websites":[18],"are":[19,190],"a":[20,26,64,77,139,211],"threat":[21],"development":[24],"of":[25,29,104,196,225],"child.":[27],"Classification":[28],"web":[30,90,256],"pages":[31],"domains":[33],"and":[34,71,134,147,167,186,236,245],"other":[35],"approaches":[36],"has":[37,54,222],"been":[38,55],"trend":[40],"due":[41],"performance":[44,95,103],"it":[45],"offering":[47],"compared":[48],"content-based":[50],"detection.":[51],"Domain-based":[52],"detection":[53],"problematic":[56],"in":[57,76,123,192],"detecting":[58],"pornographic":[59,89,191],"libraries.":[60],"This":[61,240],"study":[62,125,241],"utilizes":[63],"chrome":[65,81,99,106],"plugin":[66,82,107],"parses":[68],"all":[69,111,234],"images":[70,113,235],"deploys":[72],"nude":[73,141,148],"classifier":[74,121,142,174,221],"models":[75],"REST":[78],"endpoint.":[79],"The":[80,92,101,119,200,219],"image":[83,120,135,158,161,179,181,198,228],"parser":[84],"was":[85,96,175,208],"tested":[86],"with":[87],"2100":[88],"pages.":[91,257],"javascript":[93],"execution":[94],"collected":[97],"devTools.":[100],"average":[102],"finish":[109],"parsing":[110,233],"3":[115],"minutes.":[118],"used":[122,209],"this":[124,154],"nudenet":[127],"which":[128],"works":[129],"both":[130],"on":[131,255],"video":[133],"classification.":[136],"Nudenet":[137],"pre-trained":[140],"detects":[144],"sexual":[145],"organs":[146],"objects":[149],"deep":[151],"learning.":[152],"In":[153],"study,":[155],"we":[156],"define":[157],"descriptors":[159,229],"as":[160,210],"sources,":[162],"titles,":[163,180],"tags,":[164],"Html":[165],"siblings,":[166,185],"sources.":[168],"A":[169,194],"Support":[170],"Vector":[171],"Machine":[172],"(SVM)":[173],"created":[176],"classify":[178],"filenames,":[182],"Text":[183],"HTML":[184,238],"sources":[187],"if":[188],"they":[189],"nature.":[193],"total":[195],"7230":[197],"descriptors.":[199],"Term":[201],"Frequency":[202,206],"\u2013":[203],"Inverse":[204],"Document":[205],"(TF-IDF)":[207],"vectorizer":[212],"convert":[214],"text":[215],"data":[216],"vectors.":[218],"SVM":[220],"an":[223,243],"accuracy":[224],"76%.":[226],"Parsing":[227],"performs":[230],"faster":[231],"than":[232],"body":[237],"text.":[239],"shows":[242],"experimental":[244],"partial":[246],"result":[247],"for":[248],"Child":[249],"Sexual":[250],"Exploitation":[251],"Material":[252],"(CSEM)":[253],"tagging":[254]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}