{"id":"https://openalex.org/W2999578345","doi":"https://doi.org/10.1145/3383583.3398513","title":"The Archives Unleashed Project: Technology, Process, and Community to Improve Scholarly Access to Web Archives","display_name":"The Archives Unleashed Project: Technology, Process, and Community to Improve Scholarly Access to Web Archives","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W2999578345","doi":"https://doi.org/10.1145/3383583.3398513","mag":"2999578345"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.05399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018146166","display_name":"Nick Ruest","orcid":"https://orcid.org/0000-0003-1891-1112"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Ruest","raw_affiliation_strings":["York University Libraries, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University Libraries, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090277859","display_name":"Ian Milligan","orcid":"https://orcid.org/0000-0002-1470-7723"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ian Milligan","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011545451","display_name":"Samantha Fritz","orcid":"https://orcid.org/0000-0001-9968-4171"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Samantha Fritz","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"157","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":0.9987000226974487,"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":0.9987000226974487,"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":0.9955000281333923,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/world-wide-web","display_name":"World Wide Web","score":0.7263203859329224},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.634388267993927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6227669715881348},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5898483395576477},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5524711012840271},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.5489448308944702},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.49549973011016846},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46949058771133423},{"id":"https://openalex.org/keywords/digital-archives","display_name":"Digital Archives","score":0.4657846987247467},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3791922926902771}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7263203859329224},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.634388267993927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227669715881348},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5898483395576477},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5524711012840271},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.5489448308944702},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.49549973011016846},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46949058771133423},{"id":"https://openalex.org/C2780157182","wikidata":"https://www.wikidata.org/wiki/Q11154625","display_name":"Digital Archives","level":2,"score":0.4657846987247467},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3791922926902771},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3383583.3398513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.05399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.05399","pdf_url":"https://arxiv.org/pdf/2001.05399","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:yorkspace.library.yorku.ca:10315/37506","is_oa":true,"landing_page_url":"https://yorkspace.library.yorku.ca/xmlui/handle/10315/37506","pdf_url":"https://yorkspace.library.yorku.ca/bitstreams/2f463019-193f-409f-8145-453d3a8a8bae/download","source":{"id":"https://openalex.org/S4306400473","display_name":"YorkSpace (York University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I192455969","host_organization_name":"York University","host_organization_lineage":["https://openalex.org/I192455969"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"mag:2999578345","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.05399.pdf","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.2001.05399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.05399","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.05399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.05399","pdf_url":"https://arxiv.org/pdf/2001.05399","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"},{"id":"https://openalex.org/F4320322676","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2125910575","https://openalex.org/W2357381334","https://openalex.org/W2417849518","https://openalex.org/W2593494512","https://openalex.org/W2600418994","https://openalex.org/W2607452914","https://openalex.org/W2734766782","https://openalex.org/W2740290295","https://openalex.org/W2893710235","https://openalex.org/W2916572269","https://openalex.org/W2945842971","https://openalex.org/W2955417098","https://openalex.org/W2968239456","https://openalex.org/W2968267889","https://openalex.org/W2969129792","https://openalex.org/W2994490802","https://openalex.org/W3208133639","https://openalex.org/W3211829759","https://openalex.org/W4233776182","https://openalex.org/W4249204266","https://openalex.org/W4300801043","https://openalex.org/W4382682204","https://openalex.org/W4394021929"],"related_works":["https://openalex.org/W3046778041","https://openalex.org/W39960795","https://openalex.org/W300178524","https://openalex.org/W2530696953","https://openalex.org/W3149437954","https://openalex.org/W2626722348","https://openalex.org/W2900312065","https://openalex.org/W1583667855","https://openalex.org/W2979198026","https://openalex.org/W2174167562","https://openalex.org/W2767831356","https://openalex.org/W1970092061","https://openalex.org/W2567243404","https://openalex.org/W2940806094","https://openalex.org/W2621245226","https://openalex.org/W2577232253","https://openalex.org/W2365001484","https://openalex.org/W2049767938","https://openalex.org/W1987133604","https://openalex.org/W2963171410"],"abstract_inverted_index":{"The":[0,51],"Archives":[1,99,118],"Unleashed":[2,100,119],"project":[3],"aims":[4],"to":[5,9,93,132],"improve":[6],"scholarly":[7,64,109],"access":[8,131],"web":[10,133,164],"archives":[11,134],"through":[12],"a":[13,59,150],"multi-pronged":[14],"strategy":[15],"involving":[16],"tool":[17],"creation,":[18],"process":[19,60],"modeling,":[20],"and":[21,44,73,88,121],"community":[22],"building---all":[23],"proceeding":[24],"concurrently":[25],"in":[26,55],"mutually-reinforcing":[27],"efforts.":[28],"As":[29],"we":[30,39],"near":[31],"the":[32,49,77,117,141],"end":[33],"of":[34,163],"our":[35,42,98,145],"initially-conceived":[36],"three-year":[37],"project,":[38],"report":[40],"on":[41,76],"progress":[43],"share":[45],"lessons":[46],"learned":[47],"along":[48],"way.":[50],"main":[52,68],"contribution":[53],"articulated":[54],"this":[56],"paper":[57],"is":[58,91],"model":[61],"that":[62,79,102],"decomposes":[63],"inquiries":[65],"into":[66],"four":[67],"activities:":[69],"filter,":[70],"extract,":[71],"aggregate,":[72],"visualize.":[74],"Based":[75],"insight":[78],"these":[80,114],"activities":[81],"can":[82,112],"be":[83],"disaggregated":[84],"across":[85],"time,":[86],"space,":[87],"tools,":[89],"it":[90],"possible":[92],"generate":[94],"\"derivative":[95],"products\",":[96],"using":[97],"Toolkit,":[101],"serve":[103],"as":[104],"useful":[105],"starting":[106],"points":[107],"for":[108],"inquiry.":[110],"Scholars":[111],"download":[113],"products":[115],"from":[116,154],"Cloud":[120],"manipulate":[122],"them":[123],"just":[124],"like":[125],"any":[126,137],"other":[127],"dataset,":[128],"thus":[129],"providing":[130],"without":[135],"requiring":[136],"specialized":[138],"knowledge.":[139],"Over":[140],"past":[142],"few":[143],"years,":[144],"platform":[146],"has":[147],"processed":[148],"over":[149,155],"thousand":[151],"different":[152],"collections":[153],"two":[156],"hundred":[157],"users,":[158],"totaling":[159],"around":[160],"300":[161],"terabytes":[162],"archives.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
