{"id":"https://openalex.org/W2296090195","doi":"https://doi.org/10.1007/978-3-319-27932-9_14","title":"Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives","display_name":"Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2296090195","doi":"https://doi.org/10.1007/978-3-319-27932-9_14","mag":"2296090195"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-27932-9_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-27932-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-27932-9_14","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020179449","display_name":"Tarcisio Souza","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tarcisio Souza","raw_affiliation_strings":["L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087621364","display_name":"Elena Demidova","orcid":"https://orcid.org/0000-0002-5134-9072"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elena Demidova","raw_affiliation_strings":["L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070155789","display_name":"Thomas Risse","orcid":"https://orcid.org/0000-0001-6248-1709"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]},{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Risse","raw_affiliation_strings":["L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080662484","display_name":"Helge Holzmann","orcid":"https://orcid.org/0000-0003-4811-6902"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Helge Holzmann","raw_affiliation_strings":["L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089787580","display_name":"Gerhard Gossen","orcid":"https://orcid.org/0000-0001-8492-1103"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Gossen","raw_affiliation_strings":["L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center and Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150","https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090237397","display_name":"Julian Szyma\u0144ski","orcid":"https://orcid.org/0000-0001-5029-6768"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Julian Szymanski","raw_affiliation_strings":["Gdansk University of Technology, Gda\u0144sk, Poland"],"affiliations":[{"raw_affiliation_string":"Gdansk University of Technology, Gda\u0144sk, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020179449"],"corresponding_institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":3.4254,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93292919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9923999905586243,"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/T11719","display_name":"Data Quality and Management","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.889736533164978},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5682080388069153},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.544842541217804},{"id":"https://openalex.org/keywords/semantic-analytics","display_name":"Semantic analytics","score":0.5262241363525391},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5203285217285156},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4930274188518524},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41636112332344055},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.39519983530044556},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.25559961795806885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16599619388580322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889736533164978},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5682080388069153},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.544842541217804},{"id":"https://openalex.org/C148792806","wikidata":"https://www.wikidata.org/wiki/Q7449046","display_name":"Semantic analytics","level":4,"score":0.5262241363525391},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5203285217285156},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4930274188518524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41636112332344055},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.39519983530044556},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25559961795806885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16599619388580322}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-319-27932-9_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-27932-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1702.00619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.00619","pdf_url":"https://arxiv.org/pdf/1702.00619","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/16416","is_oa":true,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/16416","pdf_url":null,"source":{"id":"https://openalex.org/S4306401575","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Semantic keyword-based search on structured data sources : first COST Action IC1302 International KEYSTONE Conference, IKC 2015","raw_type":"status-type:publishedVersion"},{"id":"doi:10.15488/16289","is_oa":true,"landing_page_url":"https://doi.org/10.15488/16289","pdf_url":null,"source":{"id":"https://openalex.org/S7407052956","display_name":"Leibniz Universit\u00e4t Hannover","issn_l":null,"issn":[],"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:10.1007/978-3-319-27932-9_14","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-27932-9_14","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3601516360","display_name":null,"funder_award_id":"Brazil","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3989083791","display_name":null,"funder_award_id":"scholar","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2192748","https://openalex.org/W187494313","https://openalex.org/W1595552350","https://openalex.org/W1984868580","https://openalex.org/W2003471189","https://openalex.org/W2023374068","https://openalex.org/W2030169323","https://openalex.org/W2055886766","https://openalex.org/W2067698488","https://openalex.org/W2110520505","https://openalex.org/W2134491992","https://openalex.org/W2152929147","https://openalex.org/W2164052363","https://openalex.org/W2279259627"],"related_works":["https://openalex.org/W2366430559","https://openalex.org/W2349698472","https://openalex.org/W1985801232","https://openalex.org/W2023110884","https://openalex.org/W2005492920","https://openalex.org/W2355823470","https://openalex.org/W1710908466","https://openalex.org/W1975429881","https://openalex.org/W2359143405","https://openalex.org/W2016570368"],"abstract_inverted_index":{"Long-term":[0],"Web":[1,4,32,58,78,120,138,185,200],"archives":[2,59],"comprise":[3],"documents":[5,56,79],"gathered":[6],"over":[7],"longer":[8],"time":[9,154],"periods":[10],"and":[11,84,140,187],"can":[12,26,80,85,173],"easily":[13],"reach":[14],"hundreds":[15],"of":[16,38,75,106,126,144,181,199],"terabytes":[17],"in":[18,69,118,134,152,183],"size.":[19],"Semantic":[20],"annotations":[21,94],"such":[22,110],"as":[23,111],"named":[24,112,128,170],"entities":[25],"facilitate":[27],"intelligent":[28],"access":[29,54],"to":[30,53,90,115,158,160,177,193],"the":[31,36,39,55,76,96,104,116,124,127,132,135,142,145,153],"archive":[33,41,186],"data.":[34],"However,":[35],"annotation":[37],"entire":[40],"content":[42],"on":[43],"this":[44,100],"scale":[45,197],"is":[46,60],"often":[47],"infeasible.":[48],"The":[49,73],"most":[50],"efficient":[51,88],"way":[52,89],"within":[57],"provided":[61],"through":[62],"their":[63],"URLs,":[64],"which":[65,161],"are":[66,164],"typically":[67],"stored":[68],"dedicated":[70],"index":[71],"files.":[72],"URLs":[74,117,133,147,182],"archived":[77,97,146],"contain":[81],"semantic":[82,93,107],"information":[83],"offer":[86],"an":[87],"obtain":[91],"initial":[92],"for":[95],"documents.":[98,201],"In":[99],"paper,":[101],"we":[102],"analyse":[103,141],"applicability":[105],"analysis":[108],"techniques":[109,163],"entity":[113,129,171],"extraction":[114,130],"a":[119,178,189],"archive.":[121],"We":[122],"evaluate":[123],"precision":[125],"from":[131,148,156],"Popular":[136],"German":[137],"dataset":[139],"proportion":[143],"1,444":[149],"popular":[150],"domains":[151],"interval":[155],"2000":[157],"2012":[159],"these":[162],"applicable.":[165],"Our":[166],"results":[167],"demonstrate":[168],"that":[169],"recognition":[172],"be":[174],"successfully":[175],"applied":[176],"large":[179,196],"number":[180],"our":[184],"provide":[188],"good":[190],"starting":[191],"point":[192],"efficiently":[194],"annotate":[195],"collections":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
