{"id":"https://openalex.org/W4386517356","doi":"https://doi.org/10.1145/3600046.3600053","title":"From Roots to Fruits: Exploring Lineage for Dataset Recommendations","display_name":"From Roots to Fruits: Exploring Lineage for Dataset Recommendations","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4386517356","doi":"https://doi.org/10.1145/3600046.3600053"},"language":"en","primary_location":{"id":"doi:10.1145/3600046.3600053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600046.3600053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM Data Economy Workshop","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":null,"display_name":"Tarun Kumar","orcid":"https://orcid.org/0000-0001-6265-629X"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tarun Kumar","raw_affiliation_strings":["Hewlett Packard Enterprise, India"],"raw_orcid":"https://orcid.org/0000-0001-6265-629X","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, India","institution_ids":["https://openalex.org/I4210117576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033227006","display_name":"Arpit Shah","orcid":"https://orcid.org/0009-0002-2208-1238"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arpit Shah","raw_affiliation_strings":["Hewlett Packard Enterprise, India"],"raw_orcid":"https://orcid.org/0009-0002-2208-1238","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, India","institution_ids":["https://openalex.org/I4210117576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072531690","display_name":"Ashish Mishra","orcid":"https://orcid.org/0009-0007-0260-4755"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Mishra","raw_affiliation_strings":["Hewlett Packard Enterprise, India"],"raw_orcid":"https://orcid.org/0009-0007-0260-4755","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, India","institution_ids":["https://openalex.org/I4210117576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105513963","display_name":"Suparna Bhattacharya","orcid":"https://orcid.org/0000-0001-9541-4027"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suparna Bhattacharya","raw_affiliation_strings":["Hewlett Packard Enterprise, India"],"raw_orcid":"https://orcid.org/0000-0001-9541-4027","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, India","institution_ids":["https://openalex.org/I4210117576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046199130","display_name":"Arun Mahendran","orcid":"https://orcid.org/0009-0005-1151-8977"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Mahendran","raw_affiliation_strings":["Hewlett Packard Enterprise, India"],"raw_orcid":"https://orcid.org/0009-0005-1151-8977","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, India","institution_ids":["https://openalex.org/I4210117576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040323973","display_name":"Ted Dunning","orcid":"https://orcid.org/0000-0002-7655-673X"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Dunning","raw_affiliation_strings":["Hewlett Packard Enterprise, USA"],"raw_orcid":"https://orcid.org/0000-0002-7655-673X","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, USA","institution_ids":["https://openalex.org/I4210122178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092770355","display_name":"Glyn Bowden","orcid":"https://orcid.org/0009-0009-9266-4210"},"institutions":[{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glyn Bowden","raw_affiliation_strings":["Hewlett Packard Enterprise, USA"],"raw_orcid":"https://orcid.org/0009-0009-9266-4210","affiliations":[{"raw_affiliation_string":"Hewlett Packard Enterprise, USA","institution_ids":["https://openalex.org/I4210122178"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58264474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.998199999332428,"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":0.9472813606262207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827914297580719},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7036216259002686},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6093193888664246},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.5439117550849915},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5023281574249268},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5004255771636963},{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.4644484519958496},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38276898860931396},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3383917808532715}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9472813606262207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827914297580719},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7036216259002686},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6093193888664246},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.5439117550849915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5023281574249268},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5004255771636963},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.4644484519958496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38276898860931396},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3383917808532715},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3600046.3600053","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600046.3600053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM Data Economy Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2076357412","https://openalex.org/W2154851992","https://openalex.org/W2274716813","https://openalex.org/W2547844570","https://openalex.org/W2890455095","https://openalex.org/W2926805670","https://openalex.org/W2963806188","https://openalex.org/W2969723769","https://openalex.org/W2980480643","https://openalex.org/W3013008430","https://openalex.org/W3016988636","https://openalex.org/W3097300053","https://openalex.org/W3104097132","https://openalex.org/W3153432523","https://openalex.org/W3164968002","https://openalex.org/W3192055963","https://openalex.org/W3196614708","https://openalex.org/W3199052634","https://openalex.org/W3211229017","https://openalex.org/W4288086192","https://openalex.org/W4310491435","https://openalex.org/W4316923797"],"related_works":["https://openalex.org/W1552553528","https://openalex.org/W2183628870","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2782431616","https://openalex.org/W2394393789","https://openalex.org/W2374379029","https://openalex.org/W1503116306","https://openalex.org/W4299935056","https://openalex.org/W4385414095"],"abstract_inverted_index":{"Our":[0,34,78],"research":[1],"article":[2],"presents":[3],"a":[4,31],"recommender":[5],"system":[6,35],"for":[7],"datasets,":[8],"models,":[9],"and":[10,21,43,57,69,75,85,107],"processing":[11],"steps":[12],"that":[13],"is":[14,67],"based":[15],"on":[16],"utilizing":[17],"metadata":[18,41,71],"characteristics,":[19],"content,":[20],"usage":[22,65],"history":[23,48,66],"to":[24,49,113],"understand":[25],"the":[26,38,44,54,64,70,92,108,120,123],"intent":[27],"of":[28,40,46,94,122],"artifacts":[29],"in":[30,53,61,98,111],"data":[32,100,105,125],"lineage.":[33],"utilizes":[36],"both":[37,82],"availability":[39],"characteristics":[42,55,72],"corpus":[45],"recorded":[47],"uncover":[50],"interesting":[51],"associations":[52],"space":[56],"generate":[58],"recommendations,":[59],"even":[60],"situations":[62],"where":[63],"incomplete":[68],"are":[73],"noisy":[74],"poorly":[76],"named.":[77],"results,":[79],"obtained":[80],"from":[81],"self-created":[83],"testbeds":[84],"public":[86],"benchmark":[87],"datasets":[88],"like":[89],"OpenML,":[90],"demonstrate":[91],"effectiveness":[93],"our":[95],"proposed":[96],"model":[97],"assisting":[99],"discovery":[101],"by":[102,118],"leveraging":[103],"available":[104],"content":[106],"analytical":[109],"lifecycle":[110],"order":[112],"make":[114],"automated":[115],"intelligent":[116],"suggestions":[117],"reflecting":[119],"expertise":[121],"entire":[124],"community.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}