{"id":"https://openalex.org/W2979906731","doi":"https://doi.org/10.1109/jcsse.2019.8864152","title":"DATA++: An Automated Tool for Intelligent Data Augmentation Using Wikidata","display_name":"DATA++: An Automated Tool for Intelligent Data Augmentation Using Wikidata","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2979906731","doi":"https://doi.org/10.1109/jcsse.2019.8864152","mag":"2979906731"},"language":"en","primary_location":{"id":"doi:10.1109/jcsse.2019.8864152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcsse.2019.8864152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE)","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/A5090343593","display_name":"Waran Taveekarn","orcid":null},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Waran Taveekarn","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070829662","display_name":"Chatchanin Yimudom","orcid":null},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chatchanin Yimudom","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082817108","display_name":"Supisara Sukkanta","orcid":null},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Supisara Sukkanta","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066918223","display_name":"Steven Lynden","orcid":"https://orcid.org/0000-0001-6642-6934"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Steven Lynden","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090488531","display_name":"Wudhichart Sawangphol","orcid":"https://orcid.org/0000-0001-7872-2482"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Wudhichart Sawangphol","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023506216","display_name":"Suppawong Tuarob","orcid":"https://orcid.org/0000-0002-5201-5699"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Suppawong Tuarob","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand","institution_ids":["https://openalex.org/I25399158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090343593"],"corresponding_institution_ids":["https://openalex.org/I25399158"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57587374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.998199999332428,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8692600727081299},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6193332076072693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5842605233192444},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5360107421875},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5124080777168274},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5057921409606934},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.498826265335083},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.4555869698524475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4330355226993561},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43188929557800293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4152100384235382},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.17965617775917053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692600727081299},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6193332076072693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5842605233192444},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5360107421875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5124080777168274},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5057921409606934},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.498826265335083},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.4555869698524475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4330355226993561},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43188929557800293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4152100384235382},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.17965617775917053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcsse.2019.8864152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcsse.2019.8864152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W881493556","https://openalex.org/W1880262756","https://openalex.org/W1985658893","https://openalex.org/W2121282310","https://openalex.org/W2331870320","https://openalex.org/W2500382405","https://openalex.org/W2938843971","https://openalex.org/W2941003925","https://openalex.org/W2962759806","https://openalex.org/W4200480450","https://openalex.org/W4231510805","https://openalex.org/W4246959953","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W4400413234","https://openalex.org/W3153597579","https://openalex.org/W4385336128","https://openalex.org/W4394398790","https://openalex.org/W4399455186"],"abstract_inverted_index":{"In":[0,107],"the":[1,11,22,80,133,160,173,186,209,225,234],"present,":[2],"technology":[3],"has":[4],"become":[5],"a":[6,112,117],"big":[7],"influence":[8],"that":[9,37,114,208],"impacts":[10],"lives":[12],"of":[13,21,33,52,147,179,219,231],"many":[14],"humans,":[15],"with":[16,130],"artificial":[17],"intelligence":[18],"being":[19],"one":[20],"most":[23],"influential":[24],"elements.":[25],"Creative":[26],"feature":[27],"engineering":[28],"is":[29,166,190],"an":[30,126],"important":[31],"part":[32],"machine":[34],"learning":[35],"methodology":[36],"supports":[38],"and":[39,60,76,84,100,201,228],"manipulates":[40],"existing":[41,86],"data":[42,67,74,87,92,98,128,148,163,188],"to":[43,70,82,97,103,132,155,192],"make":[44],"it":[45],"work":[46],"more":[47],"efficiently":[48],"by":[49,121,212],"modifying":[50],"dimensions":[51],"data.":[53],"Pulling":[54],"useful":[55],"information":[56,158],"from":[57,125,159],"external":[58,73,90,127,187],"sources":[59,75,93],"combining":[61],"them,":[62],"however,":[63],"are":[64,152],"cumbersome":[65],"since":[66],"engineers":[68,99],"need":[69],"manually":[71],"find":[72],"process":[77],"them.":[78],"Therefore,":[79],"ability":[81],"modify":[83],"enrich":[85,104],"automatically,":[88],"using":[89,183],"open":[91,162],"could":[94],"prove":[95],"crucial":[96],"scientists":[101],"looking":[102],"their":[105],"datasets.":[106],"this":[108],"paper,":[109],"we":[110],"propose":[111],"method":[113,197],"automatically":[115],"augments":[116],"given":[118],"structured":[119],"dataset,":[120],"inferencing":[122],"relevant":[123,157],"dimension":[124],"source":[129,189],"respect":[131],"target":[134,174],"attribute.":[135],"Specifically,":[136],"our":[137,195,213],"proposed":[138,196,214],"algorithm":[139,215],"first":[140],"creates":[141],"bloom":[142],"filters":[143,151],"for":[144,224,233],"every":[145],"instance":[146],"items.":[149],"Such":[150],"then":[153],"used":[154,191],"retrieve":[156],"linked":[161],"source,":[164],"which":[165],"later":[167],"processed":[168],"into":[169],"additional":[170],"columns":[171],"in":[172],"dataset.":[175],"A":[176],"case":[177],"study":[178],"three":[180],"real-world":[181],"datasets":[182,210],"Wikidata":[184],"as":[185],"empirically":[193],"validate":[194],"on":[198,222],"both":[199],"regression":[200,226],"classification":[202,235],"tasks.":[203],"The":[204],"experimental":[205],"results":[206],"show":[207],"augmented":[211],"yield":[216],"correlation":[217],"improvement":[218,230],"23.11":[220],"%":[221],"average":[223],"task,":[227],"ROC":[229],"86.50%":[232],"task.":[236]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
