{"id":"https://openalex.org/W1966833945","doi":"https://doi.org/10.1145/2791347.2791358","title":"Towards automated prediction of relationships among scientific datasets","display_name":"Towards automated prediction of relationships among scientific datasets","publication_year":2015,"publication_date":"2015-06-29","ids":{"openalex":"https://openalex.org/W1966833945","doi":"https://doi.org/10.1145/2791347.2791358","mag":"1966833945"},"language":"en","primary_location":{"id":"doi:10.1145/2791347.2791358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2791347.2791358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Scientific and Statistical Database Management","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/A5014235464","display_name":"Abdussalam Alawini","orcid":"https://orcid.org/0000-0003-1106-7190"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdussalam Alawini","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014301644","display_name":"David Maier","orcid":"https://orcid.org/0000-0003-4790-5619"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Maier","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001807961","display_name":"Kristin Tufte","orcid":null},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Tufte","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007124763","display_name":"Bill Howe","orcid":"https://orcid.org/0000-0001-8588-8472"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Howe","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041050225","display_name":"Rashmi Nandikur","orcid":null},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rashmi Nandikur","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014235464"],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":null,"apc_paid":null,"fwci":0.8231,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78238685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7704943418502808},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.7197269201278687},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5539118051528931},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5330793857574463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47951653599739075},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4619375467300415},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.45780420303344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40594425797462463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704943418502808},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7197269201278687},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5539118051528931},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5330793857574463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47951653599739075},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4619375467300415},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.45780420303344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40594425797462463},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2791347.2791358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2791347.2791358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},{"id":"pmh:oai:pdxscholar.library.pdx.edu:compsci_fac-1165","is_oa":false,"landing_page_url":"https://pdxscholar.library.pdx.edu/compsci_fac/162","pdf_url":null,"source":{"id":"https://openalex.org/S4377196300","display_name":"PDXScholar  (Portland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126345244","host_organization_name":"Portland State University","host_organization_lineage":["https://openalex.org/I126345244"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications and Presentations","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2480544149","display_name":null,"funder_award_id":"IIS 1064685","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1528012351","https://openalex.org/W1977714272","https://openalex.org/W1980397870","https://openalex.org/W2006426998","https://openalex.org/W2017369298","https://openalex.org/W2060098952","https://openalex.org/W2093189534","https://openalex.org/W2098516643","https://openalex.org/W2119821739","https://openalex.org/W2135473121","https://openalex.org/W2147880316","https://openalex.org/W2151577432"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W2382566571","https://openalex.org/W2349321798","https://openalex.org/W2366686860","https://openalex.org/W3036520466","https://openalex.org/W148178222","https://openalex.org/W2350859087","https://openalex.org/W2387118502","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Before":[0],"scientists":[1,22,57,77],"can":[2],"analyze,":[3],"publish,":[4],"or":[5],"share":[6],"their":[7,15,59],"data,":[8],"they":[9],"often":[10],"need":[11],"to":[12,78,96,115,154],"determine":[13,40],"how":[14,50],"datasets":[16,34,42,55,122],"are":[17,104,124],"related.":[18],"Determining":[19],"relationships":[20,52,69,83,165],"helps":[21],"identify":[23,116],"the":[24,129,136,155],"most":[25,125],"complete":[26],"version":[27],"of":[28,33,92,101,121,139,170],"a":[29,89,109,113,119],"dataset,":[30],"detect":[31],"versions":[32],"that":[35,43,64,123,162],"complement":[36],"each":[37],"other,":[38],"and":[39,128,150],"multiple":[41],"overlap.":[44],"In":[45,94],"previous":[46],"work,":[47],"we":[48,103],"showed":[49],"observable":[51],"between":[53,70,84,131],"two":[54,71],"help":[56],"recall":[58],"original":[60],"derivation":[61],"connection.":[62],"While":[63],"work":[65],"helped":[66],"with":[67,98,108,166],"identifying":[68],"datasets,":[72,102],"it":[73,80],"is":[74],"infeasible":[75],"for":[76,81],"use":[79],"finding":[82],"all":[85],"possible":[86],"pairs":[87,117],"in":[88],"large":[90],"collection":[91,120],"datasets.":[93],"order":[95],"deal":[97],"larger":[99],"numbers":[100],"extending":[105],"our":[106],"methodology":[107],"relationship-prediction":[110],"system,":[111],"ReDiscover,":[112,140],"tool":[114],"from":[118],"likely":[126],"related":[127],"relationship":[130],"them.":[132],"We":[133],"report":[134],"on":[135],"initial":[137],"design":[138],"which":[141],"uses":[142],"machine-learning":[143],"methods":[144],"such":[145],"as":[146],"Conditional":[147],"Random":[148],"Fields":[149],"Support":[151],"Vector":[152],"Machines":[153],"relationship-discovery":[156],"problem.":[157],"Our":[158],"preliminarily":[159],"evaluation":[160],"shows":[161],"ReDiscover":[163],"predicted":[164],"an":[167],"average":[168],"accuracy":[169],"87%.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}