{"id":"https://openalex.org/W2047021305","doi":"https://doi.org/10.1145/2806416.2806597","title":"Semi-Automated Text Classification for Sensitivity Identification","display_name":"Semi-Automated Text Classification for Sensitivity Identification","publication_year":2015,"publication_date":"2015-10-17","ids":{"openalex":"https://openalex.org/W2047021305","doi":"https://doi.org/10.1145/2806416.2806597","mag":"2047021305"},"language":"en","primary_location":{"id":"doi:10.1145/2806416.2806597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069942298","display_name":"Giacomo Berardi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giacomo Berardi","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082069715","display_name":"Andrea Esuli","orcid":"https://orcid.org/0000-0002-5725-4322"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Esuli","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063975186","display_name":"Fabrizio Sebastiani","orcid":"https://orcid.org/0000-0003-4221-6427"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Fabrizio Sebastiani","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069942298"],"corresponding_institution_ids":["https://openalex.org/I4210107558"],"apc_list":null,"apc_paid":null,"fwci":3.12,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92759828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1711","last_page":"1714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9987999796867371,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"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":0.8191477060317993},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6920136213302612},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6762657165527344},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.617310106754303},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6045511960983276},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5287601351737976},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.5014224052429199},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.48008447885513306},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4410802125930786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4123760163784027},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3916683793067932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34623709321022034},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13683989644050598},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06916937232017517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191477060317993},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6920136213302612},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6762657165527344},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.617310106754303},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6045511960983276},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5287601351737976},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.5014224052429199},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48008447885513306},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4410802125930786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4123760163784027},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3916683793067932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34623709321022034},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13683989644050598},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06916937232017517},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2806416.2806597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:108077","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/view/author/3545.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:dnet:people______::9429898f2d35c234011226d161b28500","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"},{"id":"pmh:oai:it.cnr:prodotti:344510","is_oa":false,"landing_page_url":"http://www.cnr.it/prodotto/i/344510","pdf_url":null,"source":{"id":"https://openalex.org/S7407055101","display_name":"CNR ExploRA","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"info:cnr-pdr/source/autori:Berardi G.; Esuli A.; Macdonald C.; Ounis I.; Sebastiani F./congresso_nome:24th ACM International Conference on Information and Knowledge Management/congresso_luogo:Melbourne, AU/congresso_data:19-23%2F10%2F2015/anno:2015/pagina_da:1711/pagina_a:1714/intervallo_pagine:1711\u20131714","raw_type":"Contributo in atti di convegno"}],"best_oa_location":{"id":"pmh:oai:dnet:people______::9429898f2d35c234011226d161b28500","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W26715418","https://openalex.org/W157181893","https://openalex.org/W968552848","https://openalex.org/W1576520375","https://openalex.org/W1993220166","https://openalex.org/W1997260010","https://openalex.org/W2017238344","https://openalex.org/W2111688776","https://openalex.org/W2140663467","https://openalex.org/W2155961949","https://openalex.org/W4234664880","https://openalex.org/W6634442568"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2118758177","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W2383043320","https://openalex.org/W4297973458","https://openalex.org/W2798648420"],"abstract_inverted_index":{"Sensitive":[0],"documents":[1,18,81,111,157],"are":[2,50],"those":[3],"that":[4,41,101],"cannot":[5],"be":[6,26],"made":[7],"public,":[8],"e.g.,":[9],"for":[10,29],"personal":[11],"or":[12],"organizational":[13],"privacy":[14],"reasons.":[15],"For":[16],"instance,":[17],"requested":[19],"through":[20],"Freedom":[21,59],"of":[22,32,51,60,70,77,88,132,144,155,164],"Information":[23,61],"mechanisms":[24],"must":[25],"manually":[27,158],"reviewed":[28],"the":[30,75,86,104,110,130,142],"presence":[31],"sensitive":[33,48],"information":[34,49],"before":[35],"their":[36],"actual":[37],"release.":[38],"Hence,":[39],"tools":[40],"can":[42],"assist":[43],"human":[44,89],"reviewers":[45],"in":[46,68,118],"spotting":[47],"great":[52],"value":[53],"to":[54,58,84,99,161],"government":[55,156],"organizations":[56],"subject":[57],"laws.":[62],"We":[63,92,140],"look":[64],"at":[65],"sensitivity":[66,122],"identification":[67,123],"terms":[69],"semi-automated":[71],"text":[72],"classification":[73],"(SATC),":[74],"task":[76],"ranking":[78,109],"automatically":[79],"classified":[80],"so":[82],"as":[83,138],"optimize":[85],"cost-effectiveness":[87],"post-checking":[90],"work.":[91],"use":[93,131],"a":[94,125,133,151],"recently":[95],"proposed":[96],"utility-theoretic":[97],"approach":[98,146],"SATC":[100],"explicitly":[102],"optimizes":[103],"chosen":[105],"effectiveness":[106],"function":[107],"when":[108],"by":[112,147],"sensitivity;":[113],"this":[114,145],"is":[115,124],"especially":[116],"useful":[117],"our":[119],"case,":[120],"since":[121],"recall-oriented":[126,134],"task,":[127],"thus":[128],"requiring":[129],"evaluation":[135],"measure":[136],"such":[137],"F2.":[139],"show":[141],"validity":[143],"running":[148],"experiments":[149],"on":[150],"multi-label":[152],"multi-class":[153],"dataset":[154],"annotated":[159],"according":[160],"different":[162],"types":[163],"sensitivity.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}
