{"id":"https://openalex.org/W4308515310","doi":"https://doi.org/10.3390/data7110153","title":"Ground Truth Dataset: Objectionable Web Content","display_name":"Ground Truth Dataset: Objectionable Web Content","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308515310","doi":"https://doi.org/10.3390/data7110153"},"language":"en","primary_location":{"id":"doi:10.3390/data7110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data7110153","pdf_url":"https://www.mdpi.com/2306-5729/7/11/153/pdf?version=1667831241","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/7/11/153/pdf?version=1667831241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063561291","display_name":"Hamza Altarturi","orcid":"https://orcid.org/0000-0002-5486-9882"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Hamza H. M. Altarturi","raw_affiliation_strings":["Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047447489","display_name":"Nor Badrul Anuar","orcid":"https://orcid.org/0000-0003-4380-5303"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Nor Badrul Anuar","raw_affiliation_strings":["Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047447489"],"corresponding_institution_ids":["https://openalex.org/I33849332"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.938,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81242691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"7","issue":"11","first_page":"153","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9994999766349792,"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":0.9994999766349792,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.8487613797187805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6590098738670349},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.44064319133758545},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43970295786857605},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4225423336029053},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42153042554855347},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41921159625053406},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4022822976112366},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28281188011169434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22329223155975342},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10368093848228455}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8487613797187805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6590098738670349},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.44064319133758545},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43970295786857605},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4225423336029053},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42153042554855347},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41921159625053406},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4022822976112366},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28281188011169434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22329223155975342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10368093848228455},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/data7110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data7110153","pdf_url":"https://www.mdpi.com/2306-5729/7/11/153/pdf?version=1667831241","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jdataj:v:7:y:2022:i:11:p:153-:d:965814","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/7/11/153/","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:960018188f334514bfa13eaa9789a249","is_oa":true,"landing_page_url":"https://doaj.org/article/960018188f334514bfa13eaa9789a249","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":"Data, Vol 7, Iss 11, p 153 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/7/11/153/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data7110153","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data; Volume 7; Issue 11; Pages: 153","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/data7110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data7110153","pdf_url":"https://www.mdpi.com/2306-5729/7/11/153/pdf?version=1667831241","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308515310.pdf","grobid_xml":"https://content.openalex.org/works/W4308515310.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W206632675","https://openalex.org/W1526831942","https://openalex.org/W2002172785","https://openalex.org/W2040750298","https://openalex.org/W2062845014","https://openalex.org/W2064938367","https://openalex.org/W2241517232","https://openalex.org/W2295216512","https://openalex.org/W2296254241","https://openalex.org/W2793336985","https://openalex.org/W2802156006","https://openalex.org/W2888458159","https://openalex.org/W2890718808","https://openalex.org/W2911725277","https://openalex.org/W2944669302","https://openalex.org/W3017123539","https://openalex.org/W3027081914","https://openalex.org/W3035379814","https://openalex.org/W3086769011","https://openalex.org/W3093641884","https://openalex.org/W3128343029","https://openalex.org/W4224222062","https://openalex.org/W4229049124","https://openalex.org/W6777570461"],"related_works":["https://openalex.org/W4249299808","https://openalex.org/W2800921325","https://openalex.org/W2207500339","https://openalex.org/W2163230867","https://openalex.org/W4307079979","https://openalex.org/W2897171874","https://openalex.org/W1987716395","https://openalex.org/W2012575882","https://openalex.org/W275430299","https://openalex.org/W1484163267"],"abstract_inverted_index":{"Cyber":[0],"parental":[1,45,69,99],"control":[2,46,70],"aims":[3],"to":[4,15],"filter":[5],"objectionable":[6,23,62,115,135],"web":[7,129,136],"content":[8,24,137],"and":[9,21,48,63,87,117,147],"prevent":[10],"children":[11],"from":[12],"being":[13],"exposed":[14],"harmful":[16],"content.":[17],"Succeeding":[18],"in":[19,94,167],"detecting":[20],"blocking":[22],"depends":[25],"heavily":[26],"on":[27],"the":[28,31,58,67,95,150,168],"accuracy":[29],"of":[30,50,66,74,90,97,124,152],"topic":[32],"model.":[33],"A":[34],"reliable":[35,80],"ground":[36,55,81,105,133,161],"truth":[37,56,82,106,134,162],"dataset":[38,107,138,163],"is":[39,57,158,164],"essential":[40],"for":[41,60],"building":[42],"effective":[43],"cyber":[44,68,98],"models":[47],"validation":[49],"new":[51],"detection":[52],"methods.":[53],"The":[54,72,160],"measurement":[59],"labeling":[61],"unobjectionable":[64,119],"websites":[65,112,116,122],"dataset.":[71],"lack":[73],"publicly":[75,166],"accessible":[76],"datasets":[77],"with":[78,113],"a":[79,85,104,132,140],"has":[83],"prevented":[84],"fair":[86],"coherent":[88],"comparison":[89],"different":[91],"methods":[92],"proposed":[93],"field":[96],"control.":[100],"This":[101],"paper":[102],"presents":[103],"that":[108],"contains":[109],"8000":[110],"labelled":[111],"4000":[114,118],"websites.":[120],"These":[121],"consist":[123],"more":[125],"than":[126],"2":[127],"million":[128],"pages.":[130],"Creating":[131],"involved":[139],"few":[141],"phases,":[142],"including":[143],"data":[144],"collection,":[145],"extraction,":[146],"labeling.":[148],"Finally,":[149],"presence":[151],"bias,":[153],"using":[154],"kappa":[155],"coefficient":[156],"measurement,":[157],"addressed.":[159],"available":[165],"Mendeley":[169],"repository.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
