{"id":"https://openalex.org/W3199052634","doi":"https://doi.org/10.1145/3460231.3478882","title":"DataHunter: A System for Finding Datasets Based on Scientific Problem Descriptions","display_name":"DataHunter: A System for Finding Datasets Based on Scientific Problem Descriptions","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3199052634","doi":"https://doi.org/10.1145/3460231.3478882","mag":"3199052634"},"language":"en","primary_location":{"id":"doi:10.1145/3460231.3478882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3478882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031600582","display_name":"Michael F\u00e4rber","orcid":"https://orcid.org/0000-0001-5458-8645"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael F\u00e4rber","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091656036","display_name":"Ann-Kathrin Leisinger","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ann-Kathrin Leisinger","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.879,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77027297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"749","last_page":"752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.8219000697135925},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7289897203445435},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5843906998634338},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5380344986915588},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5375364422798157},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5086389780044556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48808085918426514},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4464068114757538},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42270106077194214},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2501864731311798},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11858558654785156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219000697135925},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7289897203445435},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5843906998634338},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5380344986915588},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5375364422798157},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5086389780044556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48808085918426514},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4464068114757538},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42270106077194214},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2501864731311798},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11858558654785156},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460231.3478882","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3478882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2302501749","https://openalex.org/W2398936787","https://openalex.org/W2493916176","https://openalex.org/W2548265258","https://openalex.org/W2780932362","https://openalex.org/W2926805670","https://openalex.org/W2945246982","https://openalex.org/W2963626623","https://openalex.org/W2964110616","https://openalex.org/W2969723769","https://openalex.org/W2970416940","https://openalex.org/W2970771982","https://openalex.org/W2980480643","https://openalex.org/W2980508402","https://openalex.org/W2981120761","https://openalex.org/W3005606952","https://openalex.org/W3205599464","https://openalex.org/W4288086192"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W599624254"],"abstract_inverted_index":{"The":[0],"number":[1],"of":[2,23,27],"datasets":[3,31,62,79,133],"is":[4,89,148],"steadily":[5],"rising,":[6],"making":[7],"it":[8],"increasingly":[9],"difficult":[10],"for":[11,32,63,93,123],"researchers":[12],"and":[13,54,97,137,144],"practitioners":[14],"in":[15,58],"the":[16,28,51,72,94,100,125,141],"various":[17],"scientific":[18],"disciplines":[19],"to":[20,80,140],"be":[21],"aware":[22],"all":[24],"datasets,":[25,112],"particularly":[26],"most":[29],"relevant":[30],"a":[33,149],"given":[34,84],"research":[35,65,85,120,152],"problem.":[36],"To":[37],"this":[38,68],"end,":[39],"dataset":[40,146],"search":[41],"engines":[42],"have":[43,56],"been":[44],"proposed.":[45],"However,":[46],"they":[47],"are":[48],"based":[49,82,90],"on":[50,83,91],"users\u2019":[52],"keywords":[53],"thus":[55],"difficulties":[57],"determining":[59],"precisely":[60],"fitting":[61],"complex":[64],"problems.":[66],"In":[67],"paper,":[69],"we":[70],"propose":[71],"system":[73,129],"at":[74],"http://data-hunter.io":[75],"that":[76,131,145],"recommends":[77],"suitable":[78],"users":[81],"problem":[86,121],"descriptions.":[87],"It":[88],"fastText":[92],"text":[95,98],"representation":[96],"classification,":[99],"Data":[101],"Set":[102],"Knowledge":[103],"Graph":[104],"(DSKG)":[105],"with":[106],"metadata":[107],"about":[108],"almost":[109],"1,700":[110],"unique":[111],"as":[113,115,119],"well":[114],"88,000":[116],"paper":[117],"abstracts":[118],"descriptions":[122],"training":[124],"model.":[126],"Overall,":[127],"our":[128],"demonstrates":[130],"recommending":[132],"facilitates":[134],"data":[135],"provisioning":[136],"reuse":[138],"according":[139],"FAIR":[142],"principles":[143],"recommendation":[147],"promising":[150],"future":[151],"direction.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
