{"id":"https://openalex.org/W4391093129","doi":"https://doi.org/10.1109/bigdata59044.2023.10386570","title":"BUILD-KG: Integrating Heterogeneous Data Into Analytics-Enabling Knowledge Graphs","display_name":"BUILD-KG: Integrating Heterogeneous Data Into Analytics-Enabling Knowledge Graphs","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093129","doi":"https://doi.org/10.1109/bigdata59044.2023.10386570"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386570","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5045531668","display_name":"Kara Schatz","orcid":"https://orcid.org/0000-0003-2310-5131"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kara Schatz","raw_affiliation_strings":["North Carolina State University,Raleigh,North Carolina,USA","North Carolina State University, Raleigh, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045326792","display_name":"Peiyu Hou","orcid":"https://orcid.org/0000-0003-0476-5812"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei-Yu Hou","raw_affiliation_strings":["North Carolina State University,Raleigh,North Carolina,USA","North Carolina State University, Raleigh, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069527267","display_name":"Alexey V. Gulyuk","orcid":"https://orcid.org/0000-0002-9924-8713"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexey V. Gulyuk","raw_affiliation_strings":["North Carolina State University,Raleigh,North Carolina,USA","North Carolina State University, Raleigh, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046770281","display_name":"Yaroslava G. Yingling","orcid":"https://orcid.org/0000-0002-8557-9992"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaroslava G. Yingling","raw_affiliation_strings":["North Carolina State University,Raleigh,North Carolina,USA","North Carolina State University, Raleigh, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078910758","display_name":"Rada Chirkova","orcid":"https://orcid.org/0000-0003-4249-9690"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rada Chirkova","raw_affiliation_strings":["North Carolina State University,Raleigh,North Carolina,USA","North Carolina State University, Raleigh, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Raleigh,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045531668"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.2897,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8274155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2965","last_page":"2974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9986000061035156,"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":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9936000108718872,"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/workflow","display_name":"Workflow","score":0.8815699219703674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8159224987030029},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.7041059136390686},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6567070484161377},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6118431687355042},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5774029493331909},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.5091750025749207},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4825684130191803},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46134573221206665},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4301034212112427},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3681909441947937},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3672519028186798},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.30476075410842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12809282541275024}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8815699219703674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159224987030029},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.7041059136390686},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6567070484161377},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6118431687355042},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5774029493331909},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.5091750025749207},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4825684130191803},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46134573221206665},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4301034212112427},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3681909441947937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3672519028186798},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30476075410842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12809282541275024},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386570","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2020278455","https://openalex.org/W2070808142","https://openalex.org/W2144578941","https://openalex.org/W2242464395","https://openalex.org/W2250539671","https://openalex.org/W2772700764","https://openalex.org/W2809106427","https://openalex.org/W2852434548","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2918428907","https://openalex.org/W2950339735","https://openalex.org/W2963718112","https://openalex.org/W3003401769","https://openalex.org/W3004611733","https://openalex.org/W3033940819","https://openalex.org/W3087991689","https://openalex.org/W3092704589","https://openalex.org/W3100825476","https://openalex.org/W3114211574","https://openalex.org/W3177015224","https://openalex.org/W3201869313","https://openalex.org/W4221142212","https://openalex.org/W4248414713","https://openalex.org/W4308206224","https://openalex.org/W4381487747","https://openalex.org/W4385574107","https://openalex.org/W6755207826","https://openalex.org/W6779811783"],"related_works":["https://openalex.org/W2019038080","https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W2794907032","https://openalex.org/W4255802207","https://openalex.org/W4299701476","https://openalex.org/W2904574413"],"abstract_inverted_index":{"Knowledge":[0],"graphs":[1],"(KGs),":[2],"with":[3,160,178],"their":[4,89],"flexible":[5],"encoding":[6],"of":[7,17,49,103],"heterogeneous":[8,76,122],"data,":[9],"have":[10],"been":[11],"increasingly":[12],"used":[13],"in":[14,28,39,61,98,146,186,198],"a":[15,70,82,115,131],"variety":[16],"applications.":[18],"At":[19],"the":[20,43,57,66,172,187],"same":[21],"time,":[22],"domain":[23,64,168,196],"data":[24,38,58,77,101,126,145,185],"are":[25],"routinely":[26],"stored":[27],"formats":[29],"such":[30,37],"as":[31,163,200],"spreadsheets,":[32],"text,":[33],"or":[34],"figures.":[35],"Storing":[36],"KGs":[40],"can":[41],"open":[42],"door":[44],"to":[45,68,156,181],"more":[46],"complex":[47],"types":[48],"analytics,":[50],"which":[51,165],"might":[52],"not":[53],"be":[54,157],"supported":[55],"by":[56],"sources":[59,80,129],"taken":[60],"isolation.":[62],"Giving":[63],"experts":[65],"option":[67],"use":[69],"predefined":[71],"automated":[72],"workflow":[73,117],"for":[74,120,194],"integrating":[75,121],"from":[78,127],"multiple":[79,128],"into":[81,130],"single":[83,132],"unified":[84,133],"KG":[85,100,134],"could":[86],"significantly":[87],"alleviate":[88],"data-integration":[90],"time":[91],"and":[92,108,124,149,183,191],"resource":[93],"burden,":[94],"while":[95],"potentially":[96,135],"resulting":[97],"higher-quality":[99],"capable":[102],"enabling":[104,136],"meaningful":[105],"rule":[106],"mining":[107],"machine":[109],"learning.In":[110],"this":[111],"paper":[112],"we":[113],"introduce":[114],"domain-agnostic":[116],"called":[118],"BUILD-KG":[119,139,152,199],"scientific":[123,182],"experimental":[125,184],"richer":[137],"analytics.":[138],"is":[140,153],"broadly":[141],"applicable,":[142],"accepting":[143],"input":[144],"popular":[147],"structured":[148],"unstructured":[150],"formats.":[151],"also":[154],"designed":[155],"carried":[158],"out":[159],"end":[161],"users":[162],"humans-in-the-loop,":[164],"makes":[166],"it":[167,180],"aware.":[169],"We":[170],"present":[171],"workflow,":[173],"report":[174],"on":[175],"our":[176],"experiences":[177],"applying":[179],"materials":[188],"science":[189],"domain,":[190],"provide":[192],"suggestions":[193],"involving":[195],"scientists":[197],"humans-in-the-loop.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}