{"id":"https://openalex.org/W4321485460","doi":"https://doi.org/10.1145/3539597.3572727","title":"Next-generation Challenges of Responsible Data Integration","display_name":"Next-generation Challenges of Responsible Data Integration","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321485460","doi":"https://doi.org/10.1145/3539597.3572727"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3572727","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3539597.3572727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","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/A5012572863","display_name":"Fatemeh Nargesian","orcid":"https://orcid.org/0000-0002-4710-8719"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Nargesian","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4710-8719","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027319416","display_name":"Abolfazl Asudeh","orcid":"https://orcid.org/0000-0002-5251-6186"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abolfazl Asudeh","raw_affiliation_strings":["University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-5251-6186","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090550596","display_name":"H. V. Jagadish","orcid":"https://orcid.org/0000-0003-0724-5214"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0003-0724-5214","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9441,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76274007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1256","last_page":"1259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"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":0.9983999729156494,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9955999851226807,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9944000244140625,"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/data-integration","display_name":"Data integration","score":0.821174144744873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7258620262145996},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6770437359809875},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5821655988693237},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.5543253421783447},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.5163925290107727},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5091835856437683},{"id":"https://openalex.org/keywords/data-governance","display_name":"Data governance","score":0.448337584733963},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.41665270924568176},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4148775339126587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.298162579536438},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.2095077633857727},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2029312551021576},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1304546296596527},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.07801079750061035}],"concepts":[{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.821174144744873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258620262145996},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6770437359809875},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5821655988693237},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.5543253421783447},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5163925290107727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5091835856437683},{"id":"https://openalex.org/C196879817","wikidata":"https://www.wikidata.org/wiki/Q872685","display_name":"Data governance","level":4,"score":0.448337584733963},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.41665270924568176},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4148775339126587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.298162579536438},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2095077633857727},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2029312551021576},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1304546296596527},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.07801079750061035},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3572727","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3539597.3572727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2513331368","display_name":null,"funder_award_id":"2107290,1741022,1934565,2107050","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W603636824","https://openalex.org/W760598031","https://openalex.org/W1819662813","https://openalex.org/W2020584928","https://openalex.org/W2148143831","https://openalex.org/W2522815997","https://openalex.org/W2798499404","https://openalex.org/W2798664493","https://openalex.org/W2896331720","https://openalex.org/W2944929477","https://openalex.org/W2948130259","https://openalex.org/W3014616325","https://openalex.org/W3031292160","https://openalex.org/W3082499364","https://openalex.org/W3085364681","https://openalex.org/W3085666889","https://openalex.org/W3139909695","https://openalex.org/W3168854329","https://openalex.org/W3171842281","https://openalex.org/W3174324482","https://openalex.org/W3175808861","https://openalex.org/W3196904276","https://openalex.org/W3197182341","https://openalex.org/W4225795800","https://openalex.org/W4312450986","https://openalex.org/W6638208828","https://openalex.org/W6766223035","https://openalex.org/W6800978076"],"related_works":["https://openalex.org/W2020045149","https://openalex.org/W2245848650","https://openalex.org/W2618163531","https://openalex.org/W3203986070","https://openalex.org/W2355440778","https://openalex.org/W2897583753","https://openalex.org/W2350326084","https://openalex.org/W2189444071","https://openalex.org/W2950687828","https://openalex.org/W2995527308"],"abstract_inverted_index":{"Data":[0],"integration":[1,52,62,79,86,113,122,146],"has":[2],"been":[3],"extensively":[4],"studied":[5],"by":[6],"the":[7,17,25,56,74,90,103,120],"data":[8,18,27,36,42,51,61,78,94,112,121,128,145,150],"management":[9],"community":[10,75],"and":[11,32,44,53,67,84,110,117,131,141],"is":[12,28],"a":[13,48],"core":[14],"task":[15],"in":[16,59,144],"pre-processing":[19],"step":[20],"of":[21,92],"ML":[22],"pipelines.":[23],"When":[24],"integrated":[26],"used":[29],"for":[30,108,115],"analysis":[31],"model":[33],"training,":[34],"responsible":[35,60,93],"science":[37],"requires":[38],"addressing":[39],"concerns":[40],"about":[41],"quality":[43,116],"bias.":[45],"We":[46,96],"present":[47],"tutorial":[49],"on":[50,98],"responsibility,":[54],"highlighting":[55],"existing":[57],"efforts":[58],"along":[63],"with":[64,81],"research":[65],"opportunities":[66],"challenges.":[68],"In":[69],"this":[70],"tutorial,":[71],"we":[72],"encourage":[73],"to":[76,105,127,133],"audit":[77],"tasks":[80,114,123],"responsibility":[82,129],"measures":[83,130],"develop":[85],"techniques":[87],"that":[88,124,147],"optimize":[89],"requirements":[91,104],"science.":[95],"focus":[97],"three":[99],"critical":[100],"aspects:":[101],"(1)":[102],"be":[106],"considered":[107],"evaluating":[109],"auditing":[111],"bias;":[118],"(2)":[119],"elicit":[125],"attention":[126],"methods":[132],"satisfy":[134],"these":[135],"requirements;":[136],"and,":[137],"(3)":[138],"techniques,":[139],"tasks,":[140],"open":[142],"problems":[143],"help":[148],"achieve":[149],"responsibility.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
