{"id":"https://openalex.org/W1984065605","doi":"https://doi.org/10.1109/tkde.2014.2320737","title":"Are Data Sets Like Documents?: Evaluating Similarity-Based Ranked Search over Scientific Data","display_name":"Are Data Sets Like Documents?: Evaluating Similarity-Based Ranked Search over Scientific Data","publication_year":2014,"publication_date":"2014-04-29","ids":{"openalex":"https://openalex.org/W1984065605","doi":"https://doi.org/10.1109/tkde.2014.2320737","mag":"1984065605"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2014.2320737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2320737","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5083399212","display_name":"V. M. Megler","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":"V. M. Megler","raw_affiliation_strings":["Department of Computer Science, Portland State University, Portland, OR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Portland State University, Portland, OR","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","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":["Department of Computer Science, Portland State University, Portland, OR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Portland State University, Portland, OR","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":5.5531,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95787169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"27","issue":"1","first_page":"32","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8049743175506592},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7616167664527893},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7012665271759033},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.5425060987472534},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5321084260940552},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.495383620262146},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4784826636314392},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41624295711517334},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37684571743011475},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36263853311538696},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24765074253082275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11649107933044434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049743175506592},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7616167664527893},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7012665271759033},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.5425060987472534},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5321084260940552},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.495383620262146},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4784826636314392},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41624295711517334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37684571743011475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36263853311538696},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24765074253082275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11649107933044434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2014.2320737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2320737","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pdxscholar.library.pdx.edu:compsci_fac-1162","is_oa":false,"landing_page_url":"https://pdxscholar.library.pdx.edu/compsci_fac/160","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G6210664664","display_name":"Science and Technology Center for Coastal Margin Observation and Prediction","funder_award_id":"0424602","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":38,"referenced_works":["https://openalex.org/W174803244","https://openalex.org/W1489817976","https://openalex.org/W1595665484","https://openalex.org/W1602022764","https://openalex.org/W1606412149","https://openalex.org/W1659561774","https://openalex.org/W1683392482","https://openalex.org/W1968927634","https://openalex.org/W1980971633","https://openalex.org/W2027382829","https://openalex.org/W2052825015","https://openalex.org/W2053528567","https://openalex.org/W2066636486","https://openalex.org/W2069870183","https://openalex.org/W2082729696","https://openalex.org/W2084863702","https://openalex.org/W2089192828","https://openalex.org/W2089680777","https://openalex.org/W2092364718","https://openalex.org/W2113640060","https://openalex.org/W2116008435","https://openalex.org/W2118516929","https://openalex.org/W2121500306","https://openalex.org/W2136009376","https://openalex.org/W2144790020","https://openalex.org/W2151664495","https://openalex.org/W2155061451","https://openalex.org/W2165723447","https://openalex.org/W2989499211","https://openalex.org/W4213009331","https://openalex.org/W4230134709","https://openalex.org/W4241445964","https://openalex.org/W4254168416","https://openalex.org/W6607131881","https://openalex.org/W6629349036","https://openalex.org/W6634990400","https://openalex.org/W6635985794","https://openalex.org/W6637466362"],"related_works":["https://openalex.org/W1976914335","https://openalex.org/W2066858118","https://openalex.org/W2134017072","https://openalex.org/W2915208987","https://openalex.org/W1940452713","https://openalex.org/W2152256925","https://openalex.org/W1994777790","https://openalex.org/W2005567565","https://openalex.org/W2806040249","https://openalex.org/W848768768"],"abstract_inverted_index":{"The":[0],"past":[1],"decade":[2],"has":[3],"seen":[4],"a":[5,56,149,162,173,183,193],"dramatic":[6],"increase":[7,22],"in":[8,28,69],"the":[9,24,30,59,64,82,94,117],"amount":[10],"of":[11,66,81,85,96,119,176],"data":[12,31,52,62,67,101,132,155,180],"captured":[13],"and":[14,122,142,187],"made":[15],"available":[16],"to":[17,34,51,54,127,145,196],"scientists":[18,26],"for":[19,99,138,164,168],"research.":[20],"This":[21],"amplifies":[23],"difficulty":[25],"face":[27],"finding":[29],"most":[32,60],"relevant":[33,61],"their":[35],"information":[36],"needs.":[37],"In":[38,111],"prior":[39],"work,":[40],"we":[41,92,114],"hypothesized":[42],"that":[43,152,154,189],"Information":[44,139],"Retrieval-style":[45],"ranked":[46,75,97,124,169,177,190],"search":[47,76,98,178,191],"can":[48],"be":[49],"applied":[50],"sets":[53,68,133,181],"help":[55],"scientist":[57],"discover":[58],"amongst":[63],"thousands":[65],"many":[70],"formats,":[71],"much":[72],"like":[73,136],"text-based":[74],"helps":[77],"users":[78,160],"make":[79],"sense":[80],"vast":[83],"number":[84],"Internet":[86],"documents.":[87],"To":[88],"test":[89],"this":[90,112],"hypothesis,":[91],"explored":[93],"use":[95],"scientific":[100],"using":[102],"an":[103],"existing":[104],"multi-terabyte":[105],"observational":[106],"archive":[107],"as":[108,161],"our":[109],"test-bed.":[110],"paper,":[113],"investigate":[115],"whether":[116],"concept":[118],"varying":[120],"relevance,":[121],"therefore":[123],"search,":[125],"applies":[126],"numeric":[128],"data-that":[129],"is,":[130],"are":[131,134],"enough":[135],"documents":[137],"Retrieval":[140],"techniques":[141],"evaluation":[143],"measures":[144],"apply?":[146],"We":[147,171],"present":[148],"user":[150,185],"study":[151,186],"demonstrates":[153],"set":[156],"similarity":[157],"resonates":[158],"with":[159,182],"basis":[163],"relevance":[165],"and,":[166],"therefore,":[167],"search.":[170],"evaluate":[172],"prototype":[174],"implementation":[175],"over":[179],"second":[184],"demonstrate":[188],"improves":[192],"scientist's":[194],"ability":[195],"find":[197],"needed":[198],"data.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}