{"id":"https://openalex.org/W1978054666","doi":"https://doi.org/10.1145/2232817.2232823","title":"Digital preservation and knowledge discovery based on documents from an international health science program","display_name":"Digital preservation and knowledge discovery based on documents from an international health science program","publication_year":2012,"publication_date":"2012-06-10","ids":{"openalex":"https://openalex.org/W1978054666","doi":"https://doi.org/10.1145/2232817.2232823","mag":"1978054666"},"language":"en","primary_location":{"id":"doi:10.1145/2232817.2232823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2232817.2232823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM/IEEE-CS 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/A5091798289","display_name":"Dharitri Misra","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dharitri Misra","raw_affiliation_strings":["National Institutes of Health, Bethesda, MD, USA","National Institutes of Health, Bethesda, Md, USA"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health, Bethesda, MD, USA","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Institutes of Health, Bethesda, Md, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006924147","display_name":"R. H. Hall","orcid":"https://orcid.org/0000-0001-8587-8696"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert H. Hall","raw_affiliation_strings":["National Institutes of Health, Bethesda, MD, USA","National Institutes of Health, Bethesda, Md, USA"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health, Bethesda, MD, USA","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Institutes of Health, Bethesda, Md, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073609587","display_name":"Susan Payne","orcid":"https://orcid.org/0000-0001-9907-3477"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan M. Payne","raw_affiliation_strings":["National Institutes of Health, Bethesda, MD, USA","National Institutes of Health, Bethesda, Md, USA"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health, Bethesda, MD, USA","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Institutes of Health, Bethesda, Md, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103701816","display_name":"George R. Thoma","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George R. Thoma","raw_affiliation_strings":["National Institutes of Health, Bethesda, MD, USA","National Institutes of Health, Bethesda, Md, USA"],"affiliations":[{"raw_affiliation_string":"National Institutes of Health, Bethesda, MD, USA","institution_ids":["https://openalex.org/I1299303238"]},{"raw_affiliation_string":"National Institutes of Health, Bethesda, Md, USA","institution_ids":["https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091798289"],"corresponding_institution_ids":["https://openalex.org/I1299303238"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14011888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9916999936103821,"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/T11937","display_name":"Research Data Management Practices","score":0.9916999936103821,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9779999852180481,"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/metadata","display_name":"Metadata","score":0.8423453569412231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7132441997528076},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6139990091323853},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5893574953079224},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5390021800994873},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.48171907663345337},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4402579665184021},{"id":"https://openalex.org/keywords/digital-preservation","display_name":"Digital preservation","score":0.42746931314468384},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4245454967021942},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40242260694503784},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17723411321640015}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8423453569412231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132441997528076},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6139990091323853},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5893574953079224},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5390021800994873},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.48171907663345337},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4402579665184021},{"id":"https://openalex.org/C2778674798","wikidata":"https://www.wikidata.org/wiki/Q632897","display_name":"Digital preservation","level":2,"score":0.42746931314468384},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4245454967021942},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40242260694503784},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17723411321640015},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2232817.2232823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2232817.2232823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332163","display_name":"U.S. Food and Drug Administration","ror":"https://ror.org/034xvzb47"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W267712887","https://openalex.org/W1560013842","https://openalex.org/W1957356093","https://openalex.org/W2093370758","https://openalex.org/W2119821739"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2021123232","https://openalex.org/W2097146382","https://openalex.org/W2137700390","https://openalex.org/W1589276137","https://openalex.org/W2566102968"],"abstract_inverted_index":{"Important":[0],"biomedical":[1],"information":[2,66,104],"is":[3],"often":[4],"recorded,":[5],"published":[6],"or":[7],"archived":[8],"in":[9,54],"unstructured":[10],"and":[11,17,32,49,52,86,99,132,167],"semi-structured":[12,117,160],"textual":[13],"form.":[14],"Artificial":[15],"intelligence":[16],"knowledge":[18],"discovery":[19],"techniques":[20,151],"may":[21],"be":[22],"applied":[23,114],"to":[24,30,41,102,115,163,174],"large":[25],"volumes":[26],"of":[27,61,75,97,119,129,140,179,187,190],"such":[28,107,170],"data":[29,84,171],"identify":[31],"extract":[33],"useful":[34],"metadata,":[35],"not":[36],"only":[37],"for":[38,46,59],"providing":[39],"access":[40],"these":[42,78,165],"documents,":[43],"but":[44],"also":[45],"conducting":[47],"analyses":[48],"uncovering":[50],"patterns":[51],"trends":[53],"a":[55,180,184,188],"field.":[56],"The":[57],"System":[58],"Preservation":[60],"Electronic":[62],"Resources":[63],"(SPER),":[64],"an":[65,95,120],"management":[67],"tool":[68],"developed":[69],"at":[70],"the":[71,116,125,136,141,150,159,177],"U.S.":[72],"National":[73],"Library":[74],"Medicine,":[76],"provides":[77],"capabilities":[79],"by":[80,152],"integrating":[81],"machine":[82],"learning,":[83],"mining":[85],"digital":[87],"preservation":[88],"techniques.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"present":[94],"overview":[96],"SPER":[98,112],"its":[100,191],"ability":[101],"retrieve":[103],"from":[105,135,158],"one":[106],"dataset.":[108],"We":[109,148],"show":[110,168],"how":[111,169],"was":[113,155,172],"records":[118],"international":[121],"health":[122,193],"science":[123,194],"program,":[124],"46-year":[126],"continuous":[127],"archive":[128],"conference":[130],"publications":[131],"related":[133],"documents":[134],"Joint":[137],"Cholera":[138],"Panel":[139],"U.S.-Japan":[142],"Cooperative":[143],"Medical":[144],"Science":[145],"Program":[146],"(CMSP).":[147],"explain":[149],"which":[153],"metadata":[154],"extracted":[156],"automatically":[157],"document":[161],"contents":[162],"preserve":[164],"publications,":[166],"used":[173],"quantitatively":[175],"describe":[176],"activity":[178],"research":[181],"community":[182],"toward":[183],"preliminary":[185],"study":[186],"subset":[189],"specific":[192],"program":[195],"goals.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
