{"id":"https://openalex.org/W3153855474","doi":"https://doi.org/10.1145/3422337.3447827","title":"A Large Publicly Available Corpus of Website Privacy Policies Based on DMOZ","display_name":"A Large Publicly Available Corpus of Website Privacy Policies Based on DMOZ","publication_year":2021,"publication_date":"2021-04-10","ids":{"openalex":"https://openalex.org/W3153855474","doi":"https://doi.org/10.1145/3422337.3447827","mag":"3153855474"},"language":"en","primary_location":{"id":"doi:10.1145/3422337.3447827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422337.3447827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh ACM Conference on Data and Application Security and Privacy","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/A5046599936","display_name":"Razieh Nokhbeh Zaeem","orcid":"https://orcid.org/0000-0002-0415-5814"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Razieh Nokhbeh Zaeem","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037778963","display_name":"K. Suzanne Barber","orcid":"https://orcid.org/0000-0003-2906-6583"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Suzanne Barber","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046599936"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.676,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84050034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9944999814033508,"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/privacy-policy","display_name":"Privacy policy","score":0.8386542201042175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057351112365723},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7179772257804871},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.6637234091758728},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.5976388454437256},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5681413412094116},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.47918450832366943},{"id":"https://openalex.org/keywords/privacy-software","display_name":"Privacy software","score":0.47654181718826294},{"id":"https://openalex.org/keywords/privacy-by-design","display_name":"Privacy by Design","score":0.43148547410964966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2823799252510071}],"concepts":[{"id":"https://openalex.org/C102938260","wikidata":"https://www.wikidata.org/wiki/Q1999831","display_name":"Privacy policy","level":3,"score":0.8386542201042175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057351112365723},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7179772257804871},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6637234091758728},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5976388454437256},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5681413412094116},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.47918450832366943},{"id":"https://openalex.org/C509729295","wikidata":"https://www.wikidata.org/wiki/Q7246032","display_name":"Privacy software","level":3,"score":0.47654181718826294},{"id":"https://openalex.org/C193934123","wikidata":"https://www.wikidata.org/wiki/Q7246028","display_name":"Privacy by Design","level":3,"score":0.43148547410964966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2823799252510071},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3422337.3447827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422337.3447827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh ACM Conference on Data and Application Security and Privacy","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1481354592","https://openalex.org/W2048089596","https://openalex.org/W2060692877","https://openalex.org/W2141105512","https://openalex.org/W2166743230","https://openalex.org/W2418038528","https://openalex.org/W2517394750","https://openalex.org/W2612622960","https://openalex.org/W2752929869","https://openalex.org/W2769124557","https://openalex.org/W2791737564","https://openalex.org/W2798397723","https://openalex.org/W2885362917","https://openalex.org/W2963070937","https://openalex.org/W2970895914","https://openalex.org/W2980748551","https://openalex.org/W3012939329","https://openalex.org/W3049637327","https://openalex.org/W3124701710"],"related_works":["https://openalex.org/W2116878667","https://openalex.org/W3042284153","https://openalex.org/W2994243660","https://openalex.org/W2118333568","https://openalex.org/W2132024542","https://openalex.org/W2154524064","https://openalex.org/W576625533","https://openalex.org/W2187353989","https://openalex.org/W2549995367","https://openalex.org/W4381737504"],"abstract_inverted_index":{"Studies":[0],"have":[1,55],"shown":[2],"website":[3],"privacy":[4,37,47,62,99,108,133,146,158,169,186],"policies":[5,38,48,63,100,109,147],"are":[6,67],"too":[7],"long":[8],"and":[9,19,30,86,121,176],"hard":[10],"to":[11,34,93,156,184],"comprehend":[12],"for":[13,125],"their":[14,103],"target":[15],"audience.":[16],"These":[17],"studies":[18],"a":[20,79,149,174],"more":[21],"recent":[22],"body":[23],"of":[24,46,60,70,83,96,98,118,144,168],"research":[25,106],"that":[26],"utilizes":[27],"machine":[28,182],"learning":[29,183],"natural":[31],"language":[32],"processing":[33],"automatically":[35],"summarize":[36,185],"greatly":[39],"benefit,":[40],"if":[41],"not":[42,68],"rely":[43],"on,":[44],"corpora":[45,59],"collected":[49],"from":[50],"the":[51,84,116,153],"web.":[52],"While":[53],"there":[54],"been":[56],"smaller":[57],"annotated":[58],"web":[61,145],"made":[64],"public,":[65],"we":[66],"aware":[69],"any":[71],"large":[72],"publicly":[73],"available":[74,124],"corpus.":[75],"We":[76,114,127],"use":[77],"DMOZ,":[78],"massive":[80],"open-content":[81],"directory":[82],"web,":[85],"its":[87],"manually":[88],"categorized":[89],"1.5":[90],"million":[91],"websites,":[92],"collect":[94],"hundreds":[95],"thousands":[97],"associated":[101],"with":[102],"categories,":[104],"enabling":[105],"on":[107],"across":[110],"different":[111,166],"categories/market":[112],"sectors.":[113],"review":[115],"statistics":[117],"this":[119],"corpus":[120,143],"make":[122],"it":[123,162],"research.":[126],"also":[128],"obtain":[129],"valuable":[130,150],"insights":[131],"about":[132],"policies,":[134],"e.g.,":[135],"which":[136],"websites":[137],"post":[138],"them":[139],"less":[140],"often.":[141],"Our":[142],"is":[148],"tool":[151],"at":[152],"researchers'":[154],"disposal":[155],"investigate":[157],"policies.":[159,187],"For":[160],"example,":[161],"facilitates":[163],"comparison":[164],"among":[165],"methods":[167],"policy":[170],"summarization":[171],"by":[172],"providing":[173],"benchmark,":[175],"can":[177],"be":[178],"used":[179],"in":[180],"unsupervised":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
