{"id":"https://openalex.org/W4399760152","doi":"https://doi.org/10.1145/3665939.3665959","title":"It Took Longer than I was Expecting: Why is Dataset Search Still so Hard?","display_name":"It Took Longer than I was Expecting: Why is Dataset Search Still so Hard?","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399760152","doi":"https://doi.org/10.1145/3665939.3665959"},"language":"en","primary_location":{"id":"doi:10.1145/3665939.3665959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665939.3665959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665939.3665959","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Workshop on Human-In-the-Loop Data Analytics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3665939.3665959","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058441702","display_name":"Madelon Hulsebos","orcid":"https://orcid.org/0000-0002-0949-7290"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Madelon Hulsebos","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110299420","display_name":"W. Lin","orcid":"https://orcid.org/0009-0007-8447-2513"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjing Lin","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023956968","display_name":"Shreya Shankar","orcid":"https://orcid.org/0000-0002-0919-9672"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreya Shankar","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Parameswaran","raw_affiliation_strings":["UC Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058441702"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.6337,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9486635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9994000196456909,"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":0.993399977684021,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767148017883301},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.776343047618866},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6847743391990662},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6171697378158569},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6003412008285522},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5799994468688965},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5403878688812256},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5274006724357605},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48781803250312805},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4226086735725403},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31843113899230957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767148017883301},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.776343047618866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6847743391990662},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6171697378158569},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6003412008285522},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5799994468688965},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5403878688812256},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5274006724357605},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48781803250312805},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4226086735725403},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31843113899230957},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3665939.3665959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665939.3665959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665939.3665959","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Workshop on Human-In-the-Loop Data Analytics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3665939.3665959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665939.3665959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665939.3665959","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Workshop on Human-In-the-Loop Data Analytics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399760152.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2058840575","https://openalex.org/W2795089200","https://openalex.org/W2926805670","https://openalex.org/W2948163032","https://openalex.org/W2951621897","https://openalex.org/W2969723769","https://openalex.org/W3146147323","https://openalex.org/W3196904276","https://openalex.org/W4327640211"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"Dataset":[0],"search":[1,97,141,170,177],"is":[2,54,142],"a":[3,23,41,49,63,145],"long-standing":[4],"problem":[5],"across":[6],"both":[7],"industry":[8,13],"and":[9,37,52,68,88,93,116,130,178],"academia.":[10],"While":[11],"most":[12,26,73,120],"tools":[14,94],"focus":[15,30],"on":[16,31],"identifying":[17,58],"one":[18],"or":[19],"more":[20],"datasets":[21],"matching":[22],"user-specified":[24],"query,":[25],"recent":[27],"academic":[28],"papers":[29],"the":[32,55,72,90,103,157,160],"subsequent":[33],"problems":[34,75],"of":[35,57,113],"join":[36,67],"union":[38,69],"discovery":[39,70],"for":[40,98,122,167],"given":[42],"dataset.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,83,137,163],"take":[48],"step":[50],"back":[51],"ask:":[53],"task":[56],"an":[59],"initial":[60],"dataset":[61,140,169],"really":[62],"solved":[64,146],"problem?":[65],"Are":[66],"indeed":[71],"pressing":[74],"to":[76,96,153],"work":[77],"on?":[78],"To":[79,155],"answer":[80],"these":[81],"questions,":[82],"survey":[84],"89":[85],"data":[86,114,123,131],"professionals":[87,124],"surface":[89],"objectives,":[91],"processes,":[92],"used":[95],"structured":[99],"datasets,":[100],"along":[101],"with":[102],"challenges":[104],"faced":[105],"when":[106],"using":[107],"existing":[108],"systems.":[109],"We":[110],"uncover":[111],"characteristics":[112],"content":[115],"metadata":[117],"that":[118,139],"are":[119],"important":[121],"during":[125],"search,":[126],"such":[127],"as":[128],"granularity":[129],"freshness.":[132],"Informed":[133],"by":[134],"our":[135],"analysis,":[136],"argue":[138],"not":[143],"yet":[144],"problem,":[147],"but":[148],"is,":[149],"in":[150,159],"fact,":[151],"difficult":[152],"solve.":[154],"move":[156],"needle":[158],"right":[161],"direction,":[162],"distill":[164],"four":[165],"desiderata":[166],"future":[168],"systems:":[171],"iterative":[172],"interfaces,":[173],"hybrid":[174],"querying,":[175],"task-driven":[176],"result":[179],"diversity.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
