{"id":"https://openalex.org/W2612167364","doi":"https://doi.org/10.1145/3041021.3054726","title":"On Automating Basic Data Curation Tasks","display_name":"On Automating Basic Data Curation Tasks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2612167364","doi":"https://doi.org/10.1145/3041021.3054726","mag":"2612167364"},"language":"en","primary_location":{"id":"doi:10.1145/3041021.3054726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3041021.3054726","pdf_url":null,"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 26th International Conference on World Wide Web Companion - WWW '17 Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3041021.3054726","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056293251","display_name":"Amin Beheshti","orcid":"https://orcid.org/0000-0002-5988-5494"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Seyed-Mehdi-Reza Beheshti","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033873399","display_name":"Alireza Tabebordbar","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alireza Tabebordbar","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042705320","display_name":"Boualem Benatallah","orcid":"https://orcid.org/0000-0002-8805-1130"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Boualem Benatallah","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016132316","display_name":"Reza Nouri","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Reza Nouri","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056293251"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":6.0715,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96303963,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"169"},"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":0.9980000257492065,"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":0.9945999979972839,"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":0.8498231172561646},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.6881318092346191},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.550237774848938},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.531073272228241},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5067251324653625},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.49528542160987854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49525895714759827},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.48933523893356323},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.4825248420238495},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4433850646018982},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4429132044315338},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.441620796918869},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42404696345329285},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3464091420173645},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.32506030797958374},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2216353416442871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498231172561646},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.6881318092346191},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.550237774848938},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.531073272228241},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5067251324653625},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.49528542160987854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49525895714759827},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.48933523893356323},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.4825248420238495},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4433850646018982},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4429132044315338},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.441620796918869},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42404696345329285},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3464091420173645},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.32506030797958374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2216353416442871},{"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:10.1145/3041021.3054726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3041021.3054726","pdf_url":null,"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 26th International Conference on World Wide Web Companion - WWW '17 Companion","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3041021.3054726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3041021.3054726","pdf_url":null,"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 26th International Conference on World Wide Web Companion - WWW '17 Companion","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W629278618","https://openalex.org/W2101196063","https://openalex.org/W2111032703","https://openalex.org/W2111532324","https://openalex.org/W2123442489","https://openalex.org/W2141975087","https://openalex.org/W2331752202","https://openalex.org/W2406996511","https://openalex.org/W2528321558","https://openalex.org/W3125862264","https://openalex.org/W4238063271"],"related_works":["https://openalex.org/W2019158987","https://openalex.org/W2142354878","https://openalex.org/W2034595671","https://openalex.org/W2281126075","https://openalex.org/W2942479669","https://openalex.org/W1601489370","https://openalex.org/W2405464607","https://openalex.org/W2594011304","https://openalex.org/W3034384113","https://openalex.org/W2044775339"],"abstract_inverted_index":{"Big":[0],"data":[1,18,22,31,36,43,62,81,87,106,126,212,227,231,244,256],"analytics":[2,19],"is":[3,47,245],"firmly":[4],"recognized":[5],"as":[6,113,141,151,177,187,201,247,263],"a":[7,102,239,248],"strategic":[8],"priority":[9],"for":[10,52,70,164,172],"modern":[11],"enterprises.":[12],"At":[13],"the":[14,21,61,78,86,92,173,196,243],"heart":[15],"of":[16,26,80,94,104,145],"big":[17],"lies":[20],"curation":[23,63,88,107,131,259],"process,":[24],"consists":[25],"tasks":[27],"that":[28,46,251],"transform":[29],"raw":[30,125],"(unstructured,":[32],"semi-structured":[33],"and":[34,44,49,56,68,77,82,90,96,100,109,117,147,162,191,206,210,222,225,242],"structured":[35,224],"sources)":[37],"into":[38,127,213,229,255],"curated":[39,128],"data,":[40],"i.e.":[41],"contextualized":[42],"knowledge":[45,170,184],"maintained":[48],"made":[50],"available":[51,112,262],"use":[53],"by":[54],"end-users":[55],"applications.":[57,232,257],"To":[58,84],"achieve":[59],"this,":[60],"process":[64,89],"may":[65],"involve":[66],"techniques":[67],"algorithms":[69],"extracting,":[71],"classifying,":[72,208],"linking,":[73],"merging,":[74],"enriching,":[75],"sampling,":[76],"summarization":[79],"knowledge.":[83],"facilitate":[85],"enhance":[91],"productivity":[93],"researchers":[95,116],"developers,":[97],"we":[98],"identify":[99],"implement":[101],"set":[103],"basic":[105],"APIs":[108,132,260],"make":[110],"them":[111,121],"services":[114,234],"to":[115,119,135,182],"developers":[118,134],"assist":[120],"in":[122],"transforming":[123],"their":[124,230],"data.":[129],"The":[130,258],"enable":[133],"easily":[136],"add":[137],"features":[138],"-":[139,228],"such":[140,150,176,186,200],"extracting":[142],"keyword,":[143],"part":[144],"speech,":[146],"named":[148],"entities":[149,181],"Persons,":[152],"Locations,":[153],"Organizations,":[154],"Companies,":[155],"Products,":[156],"Diseases,":[157],"Drugs,":[158],"etc.;":[159],"providing":[160],"synonyms":[161],"stems":[163],"extracted":[165,180,197],"information":[166,198],"items":[167],"leveraging":[168],"lexical":[169],"bases":[171,185],"English":[174],"language":[175],"WordNet;":[178],"linking":[179],"external":[183],"Google":[188],"Knowledge":[189],"Graph":[190],"Wikidata;":[192],"discovering":[193],"similarity":[194,203],"among":[195],"items,":[199],"calculating":[202],"between":[204],"string":[205],"numbers;":[207],"sorting":[209],"categorizing":[211],"various":[214],"types,":[215],"forms":[216],"or":[217],"any":[218],"other":[219],"distinct":[220],"class;":[221],"indexing":[223],"unstructured":[226],"These":[233],"can":[235,252],"be":[236,253],"accessed":[237],"via":[238],"REST":[240],"API,":[241],"returned":[246],"JSON":[249],"file":[250],"integrated":[254],"are":[261],"an":[264],"open":[265],"source":[266],"project":[267],"on":[268],"GitHub.":[269]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}