{"id":"https://openalex.org/W6888022500","doi":"https://doi.org/10.18420/informatik2021-085","title":"ExPD: Semi-automated Web Extraction of Personal Data","display_name":"ExPD: Semi-automated Web Extraction of Personal Data","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W6888022500","doi":"https://doi.org/10.18420/informatik2021-085"},"language":"en","primary_location":{"id":"doi:10.18420/informatik2021-085","is_oa":true,"landing_page_url":"https://doi.org/10.18420/informatik2021-085","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/informatik2021-085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"B\u00f6hner, Alexander","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00f6hner, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Herrmann, Dominik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herrmann, Dominik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44902779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.7932999730110168,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.7932999730110168,"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/T11719","display_name":"Data Quality and Management","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.012600000016391277,"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/task","display_name":"Task (project management)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4805999994277954},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4300999939441681},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.3799999952316284},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.36910000443458557},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.33640000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907000184059143},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4805999994277954},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.28130000829696655},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/informatik2021-085","is_oa":true,"landing_page_url":"https://doi.org/10.18420/informatik2021-085","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/informatik2021-085","is_oa":true,"landing_page_url":"https://doi.org/10.18420/informatik2021-085","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6447383165359497}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"According":[0],"to":[1,13,28,94,114],"the":[2,30,52,59,66,79,96,101],"GDPR,":[3],"data":[4,17,22,64,121],"subjects":[5],"can":[6],"issue":[7],"a":[8,21,55,82,89,133],"Subject":[9],"Access":[10],"Request":[11],"(SAR)":[12],"obtain":[14,115],"all":[15],"personal":[16,63],"concerning":[18],"them":[19],"from":[20,65],"controller.":[23],"Data":[24],"controllers":[25],"are":[26],"interested":[27],"automate":[29],"handling":[31],"of":[32,61,68,85,103,118],"SARs,":[33,104],"which":[34,129],"is":[35,49,130],"challenging":[36],"for":[37,110],"legacy":[38],"applications":[39],"and":[40],"services":[41],"that":[42,57,125],"lack":[43],"suitable":[44],"export":[45],"functionality.":[46],"This":[47],"challenge":[48],"addressed":[50],"by":[51],"ExPD":[53,72,105],"prototype,":[54],"tool":[56],"automates":[58],"task":[60],"collecting":[62],"pages":[67],"web":[69],"applications.":[70],"The":[71],"operator":[73],"specifies":[74],"extraction":[75],"rules":[76],"interactively":[77],"in":[78,132],"browser":[80],"using":[81],"small":[83],"set":[84],"pages.":[86],"After":[87],"extraction,":[88],"tool-assisted":[90],"refinement":[91],"stage":[92],"allows":[93],"fine-tune":[95],"exported":[97],"data.":[98],"Besides":[99],"automating":[100],"processing":[102],"may":[106],"also":[107],"be":[108],"useful":[109],"citizens":[111],"who":[112],"want":[113],"an":[116],"overview":[117],"their":[119],"public":[120],"footprint":[122],"on":[123],"sites":[124],"share":[126],"user":[127],"contributions,":[128],"demonstrated":[131],"case":[134],"study.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
