{"id":"https://openalex.org/W3114870588","doi":"https://doi.org/10.1145/3430984.3431032","title":"Scalable Database Normalization Powered by the Crowd","display_name":"Scalable Database Normalization Powered by the Crowd","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3114870588","doi":"https://doi.org/10.1145/3430984.3431032","mag":"3114870588"},"language":"en","primary_location":{"id":"doi:10.1145/3430984.3431032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","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/A5067329339","display_name":"GSS Aditya Sairam","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"GSS Aditya Sairam","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048564444","display_name":"Parasuram Kolli","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parasuram Kolli","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005581408","display_name":"Anudeep Immidisetty","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anudeep Immidisetty","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103944180","display_name":"Pranav Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranav Kumar","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085751067","display_name":"Madhu Sudhan B","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhu Sudhan B","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040278918","display_name":"Malay Bhattacharyya","orcid":"https://orcid.org/0000-0001-7781-1264"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Malay Bhattacharyya","raw_affiliation_strings":["Indian Statistical Institute Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067329339"],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19000239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9976999759674072,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.8805434703826904},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7872477769851685},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7735065221786499},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.735944390296936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45973408222198486},{"id":"https://openalex.org/keywords/amateur","display_name":"Amateur","score":0.4351128339767456},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.4116431474685669},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3925624191761017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39058345556259155},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32350367307662964},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.31447145342826843},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15802013874053955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805434703826904},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7872477769851685},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7735065221786499},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.735944390296936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45973408222198486},{"id":"https://openalex.org/C2778044066","wikidata":"https://www.wikidata.org/wiki/Q455595","display_name":"Amateur","level":2,"score":0.4351128339767456},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.4116431474685669},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3925624191761017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39058345556259155},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32350367307662964},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31447145342826843},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15802013874053955},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3430984.3431032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1502954553","https://openalex.org/W1537955876","https://openalex.org/W1569990199","https://openalex.org/W1571341547","https://openalex.org/W1881756506","https://openalex.org/W1973762760","https://openalex.org/W2034611273","https://openalex.org/W2045014265","https://openalex.org/W2133300352","https://openalex.org/W2158307450","https://openalex.org/W2166549982","https://openalex.org/W2168144930","https://openalex.org/W2266772167","https://openalex.org/W2271188064","https://openalex.org/W2803533046","https://openalex.org/W2907897161","https://openalex.org/W4230475127"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"In":[0,99],"the":[1,37,57,75,94],"age":[2],"of":[3,81,93,122,137],"information,":[4],"there":[5],"is":[6,48,117,133],"a":[7,113,123,126],"growing":[8],"need":[9],"to":[10,71,118],"process":[11],"data,":[12],"both":[13],"structured":[14],"and":[15,19,45,84],"unstructured,":[16],"with":[17,40],"ease":[18],"accuracy.":[20],"Such":[21],"an":[22,49,134],"intensive":[23],"task":[24,59],"might":[25],"be":[26,72],"achieved":[27],"through":[28,125],"machine":[29],"learning":[30],"based":[31],"applications,":[32],"but":[33],"not":[34,91],"always.":[35],"Moreover,":[36],"major":[38,58],"problems":[39],"existing":[41],"methodologies":[42],"are":[43],"scalability":[44],"complexity.":[46],"Crowdsourcing":[47],"alternate":[50],"solution":[51],"that":[52],"deploy":[53],"mechanisms":[54],"for":[55],"breaking":[56],"at":[60],"hand":[61],"into":[62],"smaller":[63],"segments":[64],"(microtasks)":[65],"requiring":[66],"quick":[67],"(often":[68],"binary)":[69],"decisions":[70],"exercised":[73],"by":[74],"amateur":[76],"human":[77],"participants.":[78],"The":[79,130],"use":[80],"such":[82,105],"collective":[83],"collaborative":[85],"intelligence":[86],"can":[87],"simplify":[88],"few,":[89],"if":[90],"most,":[92],"difficult":[95],"database":[96,124],"management":[97],"tasks.":[98],"this":[100],"paper,":[101],"we":[102],"address":[103],"one":[104],"problem,":[106],"precisely":[107],"determining":[108],"functional":[109],"dependencies":[110],"(FDs)":[111],"in":[112],"database.":[114],"Our":[115],"motivation":[116],"pursue":[119],"scalable":[120],"normalization":[121],"game-like":[127],"crowdsourcing":[128],"approach.":[129],"FD":[131],"realization":[132],"interesting":[135],"outcome":[136],"our":[138],"research.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}