{"id":"https://openalex.org/W2340873899","doi":"https://doi.org/10.1045/january2016-brunelle","title":"Leveraging Heritrix and the Wayback Machine on a Corporate Intranet: A Case Study on Improving Corporate Archives","display_name":"Leveraging Heritrix and the Wayback Machine on a Corporate Intranet: A Case Study on Improving Corporate Archives","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2340873899","doi":"https://doi.org/10.1045/january2016-brunelle","mag":"2340873899"},"language":"en","primary_location":{"id":"doi:10.1045/january2016-brunelle","is_oa":true,"landing_page_url":"https://doi.org/10.1045/january2016-brunelle","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1045/january2016-brunelle","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055482463","display_name":"Justin F. Brunelle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin F. Brunelle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055090088","display_name":"Krista Ferrante","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krista Ferrante","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063220040","display_name":"Eliot Wilczek","orcid":"https://orcid.org/0000-0003-4596-2126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliot Wilczek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085719625","display_name":"Michele C. Weigle","orcid":"https://orcid.org/0000-0002-2787-7166"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]},{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["GH","US"],"is_corresponding":true,"raw_author_name":"Michele C. Weigle","raw_affiliation_strings":["Old Dominion University","University of North Carolina at Chapel Hill","NASA Langley Research Center from 1991-2002"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]},{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"NASA Langley Research Center from 1991-2002","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081811192","display_name":"Michael L. Nelson","orcid":"https://orcid.org/0000-0003-3749-8116"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]},{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]},{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["GH","US"],"is_corresponding":false,"raw_author_name":"Michael L. Nelson","raw_affiliation_strings":["NASA Langley Research Center from 1991-2002","Old Dominion University","University of North Carolina at Chapel Hill"],"affiliations":[{"raw_affiliation_string":"NASA Langley Research Center from 1991-2002","institution_ids":[]},{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]},{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085719625"],"corresponding_institution_ids":["https://openalex.org/I114027177","https://openalex.org/I4210092569","https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":1.3844,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85939461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"22","issue":"1/2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9951000213623047,"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":0.9951000213623047,"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.978600025177002,"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/intranet","display_name":"Intranet","score":0.9802628755569458},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7415515780448914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6541807055473328},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43283066153526306},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4273591637611389},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.24037733674049377},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17047983407974243}],"concepts":[{"id":"https://openalex.org/C2778059363","wikidata":"https://www.wikidata.org/wiki/Q483426","display_name":"Intranet","level":3,"score":0.9802628755569458},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7415515780448914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541807055473328},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43283066153526306},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4273591637611389},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.24037733674049377},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17047983407974243},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1045/january2016-brunelle","is_oa":true,"landing_page_url":"https://doi.org/10.1045/january2016-brunelle","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},{"id":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1000","is_oa":false,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/10","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1045/january2016-brunelle","is_oa":true,"landing_page_url":"https://doi.org/10.1045/january2016-brunelle","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W257652643","https://openalex.org/W1510048484","https://openalex.org/W1553448964","https://openalex.org/W1613836731","https://openalex.org/W1773257268","https://openalex.org/W2007272345","https://openalex.org/W2012741065","https://openalex.org/W2053440061","https://openalex.org/W2082998226","https://openalex.org/W2117044215","https://openalex.org/W2293827470","https://openalex.org/W2414149432","https://openalex.org/W2913520302","https://openalex.org/W2962837245"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2374107376","https://openalex.org/W4241047679","https://openalex.org/W562045822","https://openalex.org/W2379752699","https://openalex.org/W2493140802","https://openalex.org/W2754858745","https://openalex.org/W2028692324","https://openalex.org/W2347957298","https://openalex.org/W2498491176"],"abstract_inverted_index":{"In":[0],"this":[1,37],"work,":[2],"we":[3,10],"present":[4],"a":[5,32,81],"case":[6,38],"study":[7,39],"in":[8,50],"which":[9,51],"investigate":[11],"using":[12],"open-source,":[13],"web-scale":[14],"web":[15,46,137],"archiving":[16],"tools":[17,55],"(i.e.,":[18],"Heritrix":[19],"and":[20,67,88,105,135,142],"the":[21,26,42,52,61,64,94,103,113],"Wayback":[22],"Machine":[23],"installed":[24],"on":[25,141],"MITRE":[27],"Intranet)":[28],"to":[29,40,75,91,98],"automatically":[30],"archive":[31,107],"corporate":[33,65,72],"Intranet.":[34],"We":[35,79,139],"use":[36,76,131],"outline":[41],"challenges":[43,110],"of":[44,63,83,132],"Intranet":[45,114],"archiving,":[47],"identify":[48],"situations":[49],"open":[53],"source":[54],"are":[56,96],"not":[57],"well":[58],"suited":[59],"for":[60,70,145],"needs":[62],"archivists,":[66],"make":[68,129],"recommendations":[69],"future":[71],"archivists":[73],"wishing":[74],"such":[77],"tools.":[78],"performed":[80],"crawl":[82,102],"143,268":[84],"URIs":[85],"(125":[86],"GB":[87],"25":[89],"hours)":[90],"demonstrate":[92],"that":[93],"crawlers":[95],"easy":[97],"set":[99],"up,":[100],"efficiently":[101],"Intranet,":[104],"improve":[106],"management.":[108],"However,":[109],"exist":[111],"when":[112],"contains":[115],"sensitive":[116],"information,":[117],"areas":[118],"with":[119],"potential":[120],"archival":[121,127],"value":[122],"require":[123],"user":[124],"credentials,":[125],"or":[126],"targets":[128],"extensive":[130],"internally":[133],"developed":[134],"customized":[136],"services.":[138],"elaborate":[140],"recommend":[143],"approaches":[144],"overcoming":[146],"these":[147],"challenges.":[148],"[ABSTRACT":[149],"FROM":[150],"AUTHOR]":[151]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
