{"id":"https://openalex.org/W2363111838","doi":"https://doi.org/10.1145/2910896.2910913","title":"Content Selection and Curation for Web Archiving","display_name":"Content Selection and Curation for Web Archiving","publication_year":2016,"publication_date":"2016-06-10","ids":{"openalex":"https://openalex.org/W2363111838","doi":"https://doi.org/10.1145/2910896.2910913","mag":"2363111838"},"language":"en","primary_location":{"id":"doi:10.1145/2910896.2910913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2910913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","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, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2843,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97348687,"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":"107","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T13321","display_name":"Radio, Podcasts, and Digital Media","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.737535297870636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269203662872314},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6769901514053345},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6404439210891724},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6227552890777588},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5891050100326538},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5430926084518433},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5422369837760925},{"id":"https://openalex.org/keywords/digital-curation","display_name":"Digital curation","score":0.5150182247161865},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37866684794425964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3335634469985962},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0697222650051117}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.737535297870636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269203662872314},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6769901514053345},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6404439210891724},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6227552890777588},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5891050100326538},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5430926084518433},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5422369837760925},{"id":"https://openalex.org/C2775953033","wikidata":"https://www.wikidata.org/wiki/Q5276060","display_name":"Digital curation","level":2,"score":0.5150182247161865},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37866684794425964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3335634469985962},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0697222650051117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2910896.2910913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2910913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/11649","is_oa":false,"landing_page_url":"http://hdl.handle.net/10012/11649","pdf_url":null,"source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:yorkspace.library.yorku.ca:10315/31235","is_oa":false,"landing_page_url":"http://hdl.handle.net/10315/31235","pdf_url":null,"source":{"id":"https://openalex.org/S4306401988","display_name":"York University Digital Library (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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G5788112346","display_name":null,"funder_award_id":"435-2015-0011","funder_id":"https://openalex.org/F4320334617","funder_display_name":"Social Sciences and Humanities Research Council of Canada"}],"funders":[{"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":6,"referenced_works":["https://openalex.org/W68538572","https://openalex.org/W1974106410","https://openalex.org/W2083248700","https://openalex.org/W2137187346","https://openalex.org/W2157748587","https://openalex.org/W2732645304"],"related_works":["https://openalex.org/W2400390830","https://openalex.org/W2598248896","https://openalex.org/W2907605431","https://openalex.org/W842882028","https://openalex.org/W2138555252","https://openalex.org/W2807479512","https://openalex.org/W2277259138","https://openalex.org/W3135458263","https://openalex.org/W4231012597","https://openalex.org/W3200944274"],"abstract_inverted_index":{"Any":[0],"preservation":[1],"effort":[2,131],"must":[3],"begin":[4],"with":[5],"an":[6,101,130],"assessment":[7],"of":[8,69,92,109],"what":[9],"content":[10,56],"to":[11,25,103],"preserve,":[12],"and":[13,58,136],"web":[14],"archiving":[15],"is":[16,94],"no":[17],"different.":[18],"There":[19],"have":[20,38,65],"historically":[21],"been":[22,39],"two":[23],"answers":[24],"the":[26,67,107,114],"question":[27,105],"\"what":[28],"should":[29],"we":[30,64,123],"archive?\"":[31],"The":[32,89],"Internet":[33],"Archive's":[34],"broad":[35],"entire-web":[36],"crawls":[37],"supplemented":[40],"by":[41,48,60,73,133],"narrower":[42],"domain-":[43],"or":[44],"topic-specific":[45],"collections":[46],"gathered":[47],"numerous":[49],"libraries.":[50],"We":[51,99],"can":[52,76],"characterize":[53],"this":[54,104],"as":[55,87],"selection":[57],"curation":[59],"\"gatekeepers\".":[61],"In":[62],"contrast,":[63],"witnessed":[66],"emergence":[68],"another":[70],"approach":[71,127],"driven":[72,132],"\"the":[74],"masses\"---we":[75],"archive":[77],"pages":[78],"that":[79,128],"are":[80],"contained":[81],"in":[82,106],"social":[83,134],"media":[84,135],"streams":[85],"such":[86],"Twitter.":[88],"interesting":[90],"question,":[91],"course,":[93],"how":[95],"these":[96],"approaches":[97],"differ.":[98],"provide":[100],"answer":[102],"context":[108],"a":[110,125],"case":[111],"study":[112],"about":[113],"2015":[115],"Canadian":[116],"federal":[117],"elections.":[118],"Based":[119],"on":[120],"our":[121],"analysis,":[122],"recommend":[124],"hybrid":[126],"combines":[129],"more":[137],"traditional":[138],"curatorial":[139],"methods.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
