{"id":"https://openalex.org/W2808949266","doi":"https://doi.org/10.17605/osf.io/ev42p","title":"205.3 The Many Shapes of Archive-It.","display_name":"205.3 The Many Shapes of Archive-It.","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2808949266","doi":"https://doi.org/10.17605/osf.io/ev42p","mag":"2808949266"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1806.06878","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06878","pdf_url":"https://arxiv.org/pdf/1806.06878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.06878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106487518","display_name":"Michael Nelson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008013279","display_name":"Shawn M. Jones","orcid":"https://orcid.org/0000-0002-4372-870X","observed_orcids":["https://orcid.org/0000-0002-4372-870X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jones, Shawn","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4372-870X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077830996","display_name":"Alexander C. Nwala","orcid":"https://orcid.org/0000-0003-3408-791X","observed_orcids":["https://orcid.org/0000-0003-3408-791X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nwala, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719625","display_name":"Michele C. Weigle","orcid":"https://orcid.org/0000-0002-2787-7166","observed_orcids":["https://orcid.org/0000-0002-2787-7166"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weigle, Michele","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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.9634000062942505,"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"}},"topics":[{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.9634000062942505,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.02280000038444996,"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/T13976","display_name":"Web visibility and informetrics","score":0.0026000000070780516,"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/archive-it","display_name":"Archive-It","score":0.9850000143051147},{"id":"https://openalex.org/keywords/web-archiving","display_name":"web archiving","score":0.875},{"id":"https://openalex.org/keywords/web-archives","display_name":"web archives","score":0.5509999990463257},{"id":"https://openalex.org/keywords/collection-curation","display_name":"collection curation","score":0.7080000042915344},{"id":"https://openalex.org/keywords/structural-metadata","display_name":"structural metadata","score":0.8769999742507935},{"id":"https://openalex.org/keywords/collection-metadata","display_name":"collection metadata","score":0.4359999895095825},{"id":"https://openalex.org/keywords/digital-preservation","display_name":"digital preservation","score":0.527999997138977},{"id":"https://openalex.org/keywords/internet-archive","display_name":"Internet Archive","score":0.7369999885559082}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7991410493850708},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7476351857185364},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.6805908679962158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772978901863098},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5641310811042786},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5384296178817749},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5058422088623047},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4640340805053711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4426473379135132},{"id":"https://openalex.org/C2775953033","wikidata":"https://www.wikidata.org/wiki/Q5276060","display_name":"Digital curation","level":2,"score":0.4231100082397461},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3274697959423065},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":10,"locations":[{"id":"pmh:oai:arXiv.org:1806.06878","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06878","pdf_url":"https://arxiv.org/pdf/1806.06878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:2808949266","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1806.06878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:digitalcommons.odu.edu:computerscience_fac_pubs-1250","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/computerscience_fac_pubs/246","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications","raw_type":"conference"},{"id":"pmh:oai:share.osf.io:E0187-C5C-50A","doi":null,"is_oa":false,"landing_page_url":"http://osf.io/9swfn/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"registration"},{"id":"pmh:oai:share.osf.io:E0252-761-A4D","doi":null,"is_oa":false,"landing_page_url":"http://api.osf.io/v2/nodes/ev42p/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"project"},{"id":"doi:10.48550/arxiv.1806.06878","doi":"https://doi.org/10.48550/arxiv.1806.06878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.06878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2971133053","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.06878.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.17605/osf.io/9swfn","doi":"https://doi.org/10.17605/osf.io/9swfn","is_oa":true,"landing_page_url":"https://doi.org/10.17605/osf.io/9swfn","pdf_url":null,"source":{"id":"https://openalex.org/S7407050956","display_name":"Open Science Framework","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17605/osf.io/ev42p","doi":"https://doi.org/10.17605/osf.io/ev42p","is_oa":true,"landing_page_url":"https://doi.org/10.17605/osf.io/ev42p","pdf_url":null,"source":{"id":"https://openalex.org/S7407050956","display_name":"Open Science Framework","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2895518199","doi":null,"is_oa":false,"landing_page_url":"https://osf.io/ev42p/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.06878","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.06878","pdf_url":"https://arxiv.org/pdf/1806.06878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/15","score":0.49000000953674316,"display_name":"Life on land"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W187494313","https://openalex.org/W2012741065","https://openalex.org/W2043275333","https://openalex.org/W2110793569","https://openalex.org/W2480294597","https://openalex.org/W2735186627","https://openalex.org/W2765281210","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2521425463","https://openalex.org/W3206432490","https://openalex.org/W4295940243","https://openalex.org/W2735186627","https://openalex.org/W2121661998","https://openalex.org/W2956122702","https://openalex.org/W2529227260","https://openalex.org/W2598747665","https://openalex.org/W7100986877","https://openalex.org/W4235039481"],"abstract_inverted_index":{"Web":[0],"archives,":[1],"a":[2,55,192,233,236,241],"key":[3],"area":[4],"of":[5,11,68,76,109,111,113,120,160,184,187,199,207,219,232,246],"digital":[6],"preservation,":[7],"meet":[8],"the":[9,30,51,60,66,97,158,161,185,197,211,217,229,250,253,262],"needs":[10],"journalists,":[12],"social":[13],"scientists,":[14],"historians,":[15],"and":[16,41,104,153,170,179,224,265],"government":[17],"organizations.":[18],"The":[19],"use":[20,196],"cases":[21],"for":[22,65,165],"these":[23,83,138,147,281],"groups":[24],"often":[25],"require":[26],"that":[27,149,189],"they":[28],"guide":[29],"archiving":[31],"process":[32],"themselves,":[33],"selecting":[34],"their":[35,43,73,89,270],"own":[36,44,74],"original":[37],"resources,":[38],"or":[39,80,92],"seeds,":[40,114],"creating":[42],"web":[45,78],"archive":[46],"collections.":[47,139,209],"We":[48,140,156,173],"focus":[49],"on":[50],"collections":[52,75,84,103,107,148,268],"within":[53],"Archive-It,":[54],"subscription":[56],"service":[57],"started":[58],"by":[59,269],"Internet":[61],"Archive":[62],"in":[63,118,146],"2005":[64],"purpose":[67],"allowing":[69],"organizations":[70],"to":[71,122,136,181,202,227,252,277,280],"create":[72],"archived":[77],"pages,":[79],"mementos.":[81],"Understanding":[82],"could":[85],"be":[86,278],"done":[87],"via":[88,93],"user-supplied":[90],"metadata":[91,98,131],"text":[94],"analysis,":[95],"but":[96],"is":[99,257],"applied":[100],"inconsistently":[101],"between":[102],"some":[105],"Archive-It":[106,167,208],"consist":[108],"hundreds":[110],"thousands":[112],"making":[115],"it":[116,260],"costly":[117],"terms":[119],"time":[121,264],"download":[123],"each":[124,200],"memento.":[125],"Our":[126,255],"work":[127],"proposes":[128],"using":[129,235],"structural":[130,142,213,251],"as":[132],"an":[133,182],"additional":[134],"way":[135],"understand":[137],"explore":[141],"features":[143,178],"currently":[144],"existing":[145],"can":[150],"unveil":[151],"curation":[152,169],"crawling":[154,171],"behaviors.":[155],"adapt":[157],"concept":[159],"collection":[162,168,201,234],"growth":[163],"curve":[164],"understanding":[166,183],"behavior.":[172],"also":[174],"introduce":[175],"several":[176],"seed":[177],"come":[180],"diversity":[186],"resources":[188],"make":[190],"up":[191],"collection.":[193],"Finally,":[194],"we":[195,215],"descriptions":[198],"identify":[203],"four":[204],"semantic":[205,230,271],"categories":[206],"Using":[210],"identified":[212],"features,":[214],"reviewed":[216],"results":[218],"runs":[220],"with":[221,240],"20":[222],"classifiers":[223],"are":[225],"able":[226],"predict":[228],"category":[231,272],"Random":[237],"Forest":[238],"classifier":[239],"weighted":[242],"average":[243],"F1":[244],"score":[245],"0.720,":[247],"thus":[248],"bridging":[249],"descriptive.":[254],"method":[256],"useful":[258],"because":[259],"saves":[261],"researcher":[263],"bandwidth.":[266],"Identifying":[267],"allows":[273],"further":[274],"downstream":[275],"processing":[276],"tailored":[279],"categories.":[282]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2018-06-29T00:00:00"}
