{"id":"https://openalex.org/W2795447506","doi":"https://doi.org/10.1145/3201064.3201085","title":"Focused Crawl of Web Archives to Build Event Collections","display_name":"Focused Crawl of Web Archives to Build Event Collections","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2795447506","doi":"https://doi.org/10.1145/3201064.3201085","mag":"2795447506"},"language":"en","primary_location":{"id":"doi:10.1145/3201064.3201085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.01603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073828706","display_name":"Martin Klein","orcid":"https://orcid.org/0000-0003-0130-2097"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin Klein","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA","Los Alamos National Laboratory, Los Alamos, NM USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027991610","display_name":"Lyudmila Balakireva","orcid":"https://orcid.org/0000-0002-3919-3634"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lyudmila Balakireva","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA","Los Alamos National Laboratory, Los Alamos, NM USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079585875","display_name":"Herbert Van de Sompel","orcid":"https://orcid.org/0000-0002-0715-6126"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herbert Van de Sompel","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA","Los Alamos National Laboratory, Los Alamos, NM USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073828706"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":0.44649252,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68878877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.95169997215271,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.9470999836921692,"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/crawling","display_name":"Crawling","score":0.9309242367744446},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8916500210762024},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.8066779375076294},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6983067393302917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6693918108940125},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5734155178070068},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.4955357313156128},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.4853774309158325},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4449818730354309},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4151086211204529},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3469547629356384},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07727381587028503}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9309242367744446},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8916500210762024},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.8066779375076294},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6983067393302917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693918108940125},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5734155178070068},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.4955357313156128},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.4853774309158325},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4449818730354309},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4151086211204529},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3469547629356384},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07727381587028503},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3201064.3201085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.01603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.01603","pdf_url":"https://arxiv.org/pdf/1804.01603","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":"","raw_type":null},{"id":"mag:2795447506","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1804.01603","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.01603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.01603","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.01603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.01603","pdf_url":"https://arxiv.org/pdf/1804.01603","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":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795447506.pdf","grobid_xml":"https://content.openalex.org/works/W2795447506.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W45685238","https://openalex.org/W1489992655","https://openalex.org/W1793984240","https://openalex.org/W2005579877","https://openalex.org/W2041161771","https://openalex.org/W2060966851","https://openalex.org/W2101944713","https://openalex.org/W2111346597","https://openalex.org/W2120101509","https://openalex.org/W2250837944","https://openalex.org/W2559656577","https://openalex.org/W2562321483","https://openalex.org/W2571327869","https://openalex.org/W2739703660","https://openalex.org/W3098200181","https://openalex.org/W3104829027"],"related_works":["https://openalex.org/W2963942219","https://openalex.org/W2165718336","https://openalex.org/W1503924817","https://openalex.org/W1974064905","https://openalex.org/W3184561988","https://openalex.org/W2148406518","https://openalex.org/W2185961408","https://openalex.org/W1489992655","https://openalex.org/W1965773314","https://openalex.org/W1990853665","https://openalex.org/W2529726670","https://openalex.org/W1578114322","https://openalex.org/W2116224704","https://openalex.org/W2725890098","https://openalex.org/W2058113710","https://openalex.org/W2914175568","https://openalex.org/W3171934134","https://openalex.org/W2101617672","https://openalex.org/W9131195","https://openalex.org/W2105389965"],"abstract_inverted_index":{"Event":[0],"collections":[1,95,107],"are":[2],"frequently":[3],"built":[4,108],"by":[5,17,31],"crawling":[6,22,110,127],"the":[7,11,27,36,39,43,46,52,55,65,72,77,101,111,129,149],"live":[8,112],"web":[9,21,44,85,113,131],"on":[10,71,96,128],"basis":[12],"of":[13,42,54,67,103],"seed":[14],"URIs":[15],"nominated":[16],"human":[18],"experts.":[19],"Focused":[20],"is":[23,29,57],"a":[24,58,118],"technique":[25],"where":[26],"crawler":[28],"guided":[30],"reference":[32],"content":[33],"pertaining":[34],"to":[35,89,106],"event.":[37],"Given":[38],"dynamic":[40],"nature":[41],"and":[45,99,135],"pace":[47],"with":[48],"which":[49],"topics":[50],"evolve,":[51],"timing":[53],"crawl":[56],"concern":[59],"for":[60,143],"both":[61],"approaches.":[62],"We":[63,93],"investigate":[64],"feasibility":[66],"performing":[68],"focused":[69,126],"crawls":[70],"archived":[73,130],"web.":[74],"By":[75],"utilizing":[76],"Memento":[78],"infrastructure,":[79],"we":[80],"obtain":[81],"resources":[82,105],"from":[83,109,117],"22":[84],"archives":[86],"that":[87,125,145],"contribute":[88],"building":[90],"event":[91],"collections.":[92],"create":[94],"four":[97],"events":[98,144],"compare":[100],"relevance":[102],"their":[104],"as":[114,116],"well":[115],"manually":[119],"curated":[120],"collection.":[121],"Our":[122],"results":[123,137],"show":[124],"can":[132],"be":[133],"done":[134],"indeed":[136],"in":[138,148],"highly":[139],"relevant":[140],"collections,":[141],"especially":[142],"happened":[146],"further":[147],"past.":[150]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
