{"id":"https://openalex.org/W4408395300","doi":"https://doi.org/10.1145/3709025.3712215","title":"Multilingual Scraper of Privacy Policies and Terms of Service","display_name":"Multilingual Scraper of Privacy Policies and Terms of Service","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408395300","doi":"https://doi.org/10.1145/3709025.3712215"},"language":"en","primary_location":{"id":"doi:10.1145/3709025.3712215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709025.3712215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Computer Science and Law on ZZZ","raw_type":"proceedings-article"},"type":"conference-paper","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/A5039218267","display_name":"David Bernhard","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Bernhard","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":"https://orcid.org/0009-0005-6700-7607","affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114272060","display_name":"Luka Nenadic","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luka Nenadic","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":"https://orcid.org/0009-0004-3769-7961","affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000035510","display_name":"Stefan Bechtold","orcid":"https://orcid.org/0009-0001-6259-2238"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stefan Bechtold","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":"https://orcid.org/0009-0001-6259-2238","affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102989278","display_name":"Karel Kub\u00ed\u010dek","orcid":"https://orcid.org/0000-0002-7419-2784"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Karel Kubicek","raw_affiliation_strings":["ETH Zurich, Inria"],"raw_orcid":"https://orcid.org/0000-0002-7419-2784","affiliations":[{"raw_affiliation_string":"ETH Zurich, Inria","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":9.9991,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96599431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.995199978351593,"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"}},"topics":[{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.995199978351593,"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9890999794006348,"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":0.9708999991416931,"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/scraper-site","display_name":"Scraper site","score":0.8909099698066711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6041804552078247},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5491339564323425},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.4458608031272888},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.41153717041015625},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4076511561870575},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3657683730125427},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.2835351228713989},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.05681315064430237}],"concepts":[{"id":"https://openalex.org/C78500136","wikidata":"https://www.wikidata.org/wiki/Q477840","display_name":"Scraper site","level":2,"score":0.8909099698066711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6041804552078247},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5491339564323425},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.4458608031272888},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.41153717041015625},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4076511561870575},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3657683730125427},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2835351228713989},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.05681315064430237}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3709025.3712215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709025.3712215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Computer Science and Law on ZZZ","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":41,"referenced_works":["https://openalex.org/W17416266","https://openalex.org/W2564314446","https://openalex.org/W2644877912","https://openalex.org/W2744486576","https://openalex.org/W2744987241","https://openalex.org/W2782760443","https://openalex.org/W2796381392","https://openalex.org/W2798838283","https://openalex.org/W2887427605","https://openalex.org/W2921026077","https://openalex.org/W2963611340","https://openalex.org/W2981829128","https://openalex.org/W2999830435","https://openalex.org/W3049637327","https://openalex.org/W3080917700","https://openalex.org/W3103764297","https://openalex.org/W3121736041","https://openalex.org/W3124701710","https://openalex.org/W3154337097","https://openalex.org/W3167011276","https://openalex.org/W3177181460","https://openalex.org/W3179937365","https://openalex.org/W4205891824","https://openalex.org/W4220692215","https://openalex.org/W4224319565","https://openalex.org/W4285730361","https://openalex.org/W4307020316","https://openalex.org/W4362452929","https://openalex.org/W4367022939","https://openalex.org/W4376626980","https://openalex.org/W4380838973","https://openalex.org/W4385522472","https://openalex.org/W4389403907","https://openalex.org/W4393299261","https://openalex.org/W4393927934","https://openalex.org/W4395444074","https://openalex.org/W4397019817","https://openalex.org/W4406074025","https://openalex.org/W6850422018","https://openalex.org/W6924713813","https://openalex.org/W7046277644"],"related_works":["https://openalex.org/W2584827882","https://openalex.org/W3195097297","https://openalex.org/W4225340788","https://openalex.org/W3038106605","https://openalex.org/W2513267613","https://openalex.org/W3049084372","https://openalex.org/W2528109871","https://openalex.org/W2940702331","https://openalex.org/W2905822832","https://openalex.org/W2240244939"],"abstract_inverted_index":{"Websites'":[0],"privacy":[1,63,109],"policies":[2,64,110],"and":[3,42,49,65,82,111,125],"terms":[4,66,114],"of":[5,34,51,62,96,100,106,115,133],"service":[6,116],"constitute":[7],"valuable":[8,35],"resources":[9],"for":[10,39,87,108,113,136],"scholars":[11],"in":[12,91,117],"various":[13],"disciplines.":[14],"Nonetheless,":[15],"there":[16],"exists":[17],"no":[18],"large,":[19],"multilingual":[20],"database":[21,135],"collecting":[22,37],"these":[23,43],"documents":[24,102],"over":[25],"the":[26,47,85,88,97,101],"long":[27],"term.":[28],"Therefore,":[29],"researchers":[30],"spend":[31],"a":[32,55,59,75],"lot":[33],"time":[36],"them":[38],"individual":[40],"projects,":[41],"heterogeneous":[44],"methods":[45],"impede":[46],"reproducibility":[48],"comparability":[50],"research":[52],"findings.":[53],"As":[54],"solution,":[56],"we":[57,83],"introduce":[58],"long-term":[60],"scraper":[61,73],"supporting":[67],"37":[68],"languages.":[69],"We":[70,127],"run":[71],"our":[72,134],"on":[74,78],"monthly":[76],"basis":[77],"800":[79],"000":[80],"websites,":[81],"publish":[84],"dataset":[86],"twelve":[89],"crawls":[90],"2024.":[92],"Our":[93],"manual":[94],"evaluation":[95],"end-to-end":[98],"extraction":[99],"demonstrates":[103],"F1":[104],"scores":[105],"79%":[107],"75%":[112],"five":[118],"sample":[119],"languages":[120],"(English,":[121],"German,":[122],"French,":[123],"Italian,":[124],"Croatian).":[126],"present":[128],"several":[129],"broad":[130],"potential":[131],"applications":[132],"future":[137],"research.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
