{"id":"https://openalex.org/W2963272039","doi":"https://doi.org/10.1145/3184558.3191636","title":"Can Common Crawl Reliably Track Persistent Identifier (PID) Use Over Time","display_name":"Can Common Crawl Reliably Track Persistent Identifier (PID) Use Over Time","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963272039","doi":"https://doi.org/10.1145/3184558.3191636","mag":"2963272039"},"language":"en","primary_location":{"id":"doi:10.1145/3184558.3191636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191636","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191636&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3191636&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013277522","display_name":"Henry S. Thompson","orcid":"https://orcid.org/0000-0001-5490-1347"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Henry S. Thompson","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025411088","display_name":"Jian Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jian Tong","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1749","last_page":"1755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.993399977684021,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.993399977684021,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9919999837875366,"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/T11719","display_name":"Data Quality and Management","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.8712254762649536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261869311332703},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.7247416973114014},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5709829926490784},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.507415235042572},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32745760679244995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08837839961051941},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.061228930950164795}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.8712254762649536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261869311332703},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.7247416973114014},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5709829926490784},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.507415235042572},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32745760679244995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08837839961051941},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.061228930950164795}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3184558.3191636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191636","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191636&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f88a72b3-87c7-46aa-b182-82e7ebf2424c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f88a72b3-87c7-46aa-b182-82e7ebf2424c","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Thompson, H S & Tong, J 2018, Can Common Crawl Reliably Track Persistent Identifier (PID) Use Over Time. in Companion Proceedings of the The Web Conference 2018. Lyon, France, pp. 1749-1755, The Web Conference 2018, Lyon, France, 23/04/18. https://doi.org/10.1145/3184558.3191636","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f88a72b3-87c7-46aa-b182-82e7ebf2424c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/can-common-crawl-reliably-track-persistent-identifier-pid-use-over-time(f88a72b3-87c7-46aa-b182-82e7ebf2424c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Thompson, H S & Tong, J 2018, Can Common Crawl Reliably Track Persistent Identifier (PID) Use Over Time. in Companion Proceedings of the The Web Conference 2018. Lyon, France, pp. 1749-1755, The Web Conference 2018, Lyon, France, 23/04/18. https://doi.org/10.1145/3184558.3191636","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3184558.3191636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3184558.3191636","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3191636&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G4072067573","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G777199097","display_name":null,"funder_award_id":"EPSRC grant EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8597009950","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963272039.pdf","grobid_xml":"https://content.openalex.org/works/W2963272039.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2032715459","https://openalex.org/W2046166587"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4378651134","https://openalex.org/W1979633005","https://openalex.org/W2352307597","https://openalex.org/W2163724607","https://openalex.org/W1980092392","https://openalex.org/W4318812462","https://openalex.org/W37347591","https://openalex.org/W2118976126","https://openalex.org/W4252684102"],"abstract_inverted_index":{"We":[0,104],"report":[1],"here":[2],"on":[3,48,69,108,116],"the":[4,18,36,49,58,86,97],"results":[5],"of":[6,39,41],"two":[7,10],"studies":[8,114],"using":[9],"and":[11,25,57,83,100],"four":[12],"monthly":[13],"web":[14],"crawls":[15],"respectively":[16],"from":[17,73,96],"Common":[19],"Crawl":[20],"(CC)":[21],"initiative":[22],"between":[23],"2014":[24,82],"2017,":[26,85],"whose":[27],"initial":[28],"goal":[29],"was":[30],"to":[31,112,118],"provide":[32],"empirical":[33],"evidence":[34],"for":[35,52],"changing":[37],"patterns":[38],"use":[40],"so-called":[42],"persistent":[43],"identifiers.":[44],"This":[45],"paper":[46],"focusses":[47],"tooling":[50],"needed":[51,111],"dealing":[53],"with":[54,62,106],"CC":[55,117],"data,":[56],"problems":[59],"we":[60],"found":[61],"it.":[63],"The":[64],"first":[65],"study":[66,88],"is":[67],"based":[68,115],"over":[70,74],"10^12":[71],"URIs":[72],"5":[75],"x":[76,93],"10^9":[77,94],"pages":[78,95],"crawled":[79],"in":[80],"April":[81,84,98,101],"second":[87],"adds":[89],"a":[90],"further":[91],"3":[92],"2015":[99],"2016":[102],"crawls.":[103],"conclude":[105],"suggestions":[107],"specific":[109],"actions":[110],"enable":[113],"give":[119],"reliable":[120],"longitudinal":[121],"information.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
