{"id":"https://openalex.org/W4387332921","doi":"https://doi.org/10.1145/3626521","title":"Dataset Discovery and Exploration: A Survey","display_name":"Dataset Discovery and Exploration: A Survey","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387332921","doi":"https://doi.org/10.1145/3626521"},"language":"en","primary_location":{"id":"doi:10.1145/3626521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626521","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066619159","display_name":"Norman W. Paton","orcid":"https://orcid.org/0000-0003-2008-6617"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Norman W. Paton","raw_affiliation_strings":["Department of Computer Science, University of Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-2008-6617","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085691361","display_name":"Jiaoyan Chen","orcid":"https://orcid.org/0000-0003-4643-6750"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaoyan Chen","raw_affiliation_strings":["Department of Computer Science, University of Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-4643-6750","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773431","display_name":"Zhenyu Wu","orcid":"https://orcid.org/0000-0003-0981-5567"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenyu Wu","raw_affiliation_strings":["Department of Computer Science, University of Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-0981-5567","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":6.7565,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9710512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"56","issue":"4","first_page":"1","last_page":"37"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9973000288009644,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.848450779914856},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6579272150993347},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6478760838508606},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.5560890436172485},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5237895250320435},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4948710799217224},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4892563819885254},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.482611745595932},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4732661247253418},{"id":"https://openalex.org/keywords/business-process-discovery","display_name":"Business process discovery","score":0.46078503131866455},{"id":"https://openalex.org/keywords/data-exploration","display_name":"Data exploration","score":0.44011297821998596},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42344290018081665},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.41424036026000977},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34990644454956055},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.23060405254364014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16351783275604248},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16222664713859558},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13675186038017273},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.12376043200492859},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.08513277769088745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848450779914856},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6579272150993347},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6478760838508606},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.5560890436172485},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5237895250320435},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4948710799217224},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4892563819885254},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.482611745595932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4732661247253418},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.46078503131866455},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.44011297821998596},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42344290018081665},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.41424036026000977},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34990644454956055},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.23060405254364014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16351783275604248},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16222664713859558},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13675186038017273},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.12376043200492859},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.08513277769088745},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626521","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/c882d98a-c9e9-4149-ad11-8febf02bf168","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/c882d98a-c9e9-4149-ad11-8febf02bf168","pdf_url":"https://pure.manchester.ac.uk/ws/files/278807262/3626521.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Paton, N, Chen, J & Wu, Z 2023, 'Dataset Discovery and Exploration: A Survey', ACM Computing Surveys. https://doi.org/10.1145/3626521","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3626521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626521","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387332921.pdf","grobid_xml":"https://content.openalex.org/works/W4387332921.grobid-xml"},"referenced_works_count":100,"referenced_works":["https://openalex.org/W202389787","https://openalex.org/W760598031","https://openalex.org/W1483205977","https://openalex.org/W1552847225","https://openalex.org/W1758759808","https://openalex.org/W1830657834","https://openalex.org/W1964189668","https://openalex.org/W1969621019","https://openalex.org/W1969713547","https://openalex.org/W1981951557","https://openalex.org/W1996505782","https://openalex.org/W2008896880","https://openalex.org/W2015191210","https://openalex.org/W2020022499","https://openalex.org/W2036902446","https://openalex.org/W2066806792","https://openalex.org/W2069028640","https://openalex.org/W2091359547","https://openalex.org/W2092364718","https://openalex.org/W2111869785","https://openalex.org/W2122949840","https://openalex.org/W2125510575","https://openalex.org/W2128793454","https://openalex.org/W2131785201","https://openalex.org/W2140116426","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2154475850","https://openalex.org/W2206400781","https://openalex.org/W2251264718","https://openalex.org/W2265741522","https://openalex.org/W2290320465","https://openalex.org/W2296164608","https://openalex.org/W2398606196","https://openalex.org/W2405186200","https://openalex.org/W2438792749","https://openalex.org/W2521441617","https://openalex.org/W2529049456","https://openalex.org/W2564084673","https://openalex.org/W2616147950","https://openalex.org/W2626982577","https://openalex.org/W2686965047","https://openalex.org/W2740592503","https://openalex.org/W2744739752","https://openalex.org/W2762307198","https://openalex.org/W2788550262","https://openalex.org/W2795089200","https://openalex.org/W2795302121","https://openalex.org/W2798664493","https://openalex.org/W2889133671","https://openalex.org/W2898796029","https://openalex.org/W2907544011","https://openalex.org/W2926805670","https://openalex.org/W2948163032","https://openalex.org/W2963174348","https://openalex.org/W2963224980","https://openalex.org/W2963299709","https://openalex.org/W2963341956","https://openalex.org/W2969723769","https://openalex.org/W2970059736","https://openalex.org/W2974662081","https://openalex.org/W3008881932","https://openalex.org/W3013003636","https://openalex.org/W3013008430","https://openalex.org/W3014616325","https://openalex.org/W3015245730","https://openalex.org/W3026889466","https://openalex.org/W3031051334","https://openalex.org/W3032215537","https://openalex.org/W3090271579","https://openalex.org/W3099839495","https://openalex.org/W3099965312","https://openalex.org/W3110128307","https://openalex.org/W3112768174","https://openalex.org/W3128513378","https://openalex.org/W3136005568","https://openalex.org/W3138133779","https://openalex.org/W3138890951","https://openalex.org/W3166453267","https://openalex.org/W3174181645","https://openalex.org/W3174637548","https://openalex.org/W3185492633","https://openalex.org/W3193753157","https://openalex.org/W3194262547","https://openalex.org/W3196867679","https://openalex.org/W3196877232","https://openalex.org/W3199469221","https://openalex.org/W3216718110","https://openalex.org/W4280522992","https://openalex.org/W4283819412","https://openalex.org/W4285610178","https://openalex.org/W4287271189","https://openalex.org/W4288343461","https://openalex.org/W4289533971","https://openalex.org/W4366549947","https://openalex.org/W4367858557","https://openalex.org/W6758993734","https://openalex.org/W6796263054","https://openalex.org/W6799672518","https://openalex.org/W6967422778"],"related_works":["https://openalex.org/W1989373239","https://openalex.org/W2143920642","https://openalex.org/W2060045119","https://openalex.org/W2496603770","https://openalex.org/W118909908","https://openalex.org/W2103281268","https://openalex.org/W2336675426","https://openalex.org/W2185491808","https://openalex.org/W110081222","https://openalex.org/W57948323"],"abstract_inverted_index":{"Data":[0,54,68,85],"scientists":[1],"are":[2,42,164],"tasked":[3],"with":[4],"obtaining":[5],"insights":[6],"from":[7,97],"data.":[8],"However,":[9],"suitable":[10],"data":[11,28,33,38,51,88,109,117,119],"is":[12,56,70,187],"often":[13,45,90,165],"not":[14],"immediately":[15],"at":[16],"hand,":[17],"and":[18,40,80,87,95,111,121,140,146,152,173],"there":[19],"may":[20,63],"be":[21,135],"many":[22],"potentially":[23],"relevant":[24],"datasets":[25,61,79],"in":[26,31,49,93,167],"a":[27,36,50,183],"lake":[29],"or":[30],"open":[32],"repositories.":[34],"As":[35],"result,":[37],"discovery":[39,55,86,110],"exploration":[41,69,89],"necessary,":[43],"but":[44],"time":[46],"consuming,":[47],"steps":[48],"analysis":[52],"workflow.":[53],"the":[57,71,75,81,141,148],"process":[58,72],"of":[59,73,77,126],"identifying":[60],"that":[62,105,133,163],"meet":[64],"an":[65],"information":[66],"need.":[67],"understanding":[74],"properties":[76],"candidate":[78],"relationships":[82],"between":[83],"them.":[84],"go":[91],"hand":[92,94],"benefit":[96],"tool":[98],"support.":[99],"This":[100],"article":[101],"surveys":[102],"research":[103],"areas":[104,162],"can":[106,134,144],"contribute":[107],"to":[108,137,150,176],"exploration,":[112],"particularly":[113],"considering":[114],"dataset":[115],"search,":[116],"navigation,":[118],"annotation":[120],"schema":[122],"inference.":[123],"For":[124],"each":[125],"these":[127],"areas,":[128],"we":[129,169],"identify":[130,170],"key":[131],"dimensions":[132,149],"used":[136],"characterize":[138],"approaches":[139,175],"values":[142],"they":[143],"hold,":[145],"apply":[147],"describe":[151],"compare":[153],"prominent":[154],"results.":[155],"In":[156],"addition,":[157],"by":[158],"surveying":[159],"several":[160],"adjacent":[161],"considered":[166],"isolation,":[168],"recurring":[171],"techniques":[172],"alternative":[174],"related":[177],"challenges,":[178],"thereby":[179],"placing":[180],"results":[181],"within":[182],"wider":[184],"context":[185],"than":[186],"generally":[188],"considered.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}