{"id":"https://openalex.org/W2583184028","doi":"https://doi.org/10.1109/bigdata.2016.7840935","title":"Bad big data science","display_name":"Bad big data science","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583184028","doi":"https://doi.org/10.1109/bigdata.2016.7840935","mag":"2583184028"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5043873066","display_name":"Frank S. Haug","orcid":null},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Frank S. Haug","raw_affiliation_strings":["Department of Communications Engineering, University of M\u00e1laga, M\u00e1laga, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of M\u00e1laga, M\u00e1laga, Spain","institution_ids":["https://openalex.org/I82767444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043873066"],"corresponding_institution_ids":["https://openalex.org/I82767444"],"apc_list":null,"apc_paid":null,"fwci":1.4406,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86158409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"2863","last_page":"2871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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/big-data","display_name":"Big data","score":0.8190961480140686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998502254486084},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7280981540679932},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.6540115475654602},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.6484154462814331},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5739457011222839},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5643254518508911},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4286404550075531},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42568519711494446},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3670194745063782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3258039057254791},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09342873096466064}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8190961480140686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998502254486084},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7280981540679932},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.6540115475654602},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6484154462814331},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5739457011222839},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5643254518508911},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4286404550075531},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42568519711494446},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3670194745063782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3258039057254791},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09342873096466064},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W77952428","https://openalex.org/W184387631","https://openalex.org/W642257631","https://openalex.org/W1510220247","https://openalex.org/W1522629397","https://openalex.org/W1981420413","https://openalex.org/W2029089311","https://openalex.org/W2057720927","https://openalex.org/W2144192824","https://openalex.org/W2159942800","https://openalex.org/W2165467455","https://openalex.org/W2185907055","https://openalex.org/W2207131393","https://openalex.org/W2214534990","https://openalex.org/W2350573227","https://openalex.org/W2611978019","https://openalex.org/W2624304035","https://openalex.org/W2945526390","https://openalex.org/W4246696625","https://openalex.org/W6738874634"],"related_works":["https://openalex.org/W2901826185","https://openalex.org/W2742521120","https://openalex.org/W3119296476","https://openalex.org/W2891888580","https://openalex.org/W2159392828","https://openalex.org/W2353586736","https://openalex.org/W2215544391","https://openalex.org/W2189235061","https://openalex.org/W2061985295","https://openalex.org/W2353590449"],"abstract_inverted_index":{"As":[0],"hardware":[1],"and":[2,34,47,60,81,94,110,140,154],"software":[3],"technologies":[4,35],"have":[5,84],"improved,":[6],"our":[7],"definition":[8],"of":[9,13,30,40,136],"a":[10],"\u201cmanageable":[11],"amount":[12],"data\u201d":[14,24],"has":[15],"increased":[16],"in":[17,87],"its":[18],"scope":[19],"dramatically.":[20],"The":[21,51],"term":[22,52],"\u201cbig":[23],"can":[25],"be":[26],"applied":[27],"to":[28,56,64,106],"any":[29],"several":[31],"different":[32],"projects":[33,100],"sharing":[36],"the":[37,57,67,133,137],"ultimate":[38],"goal":[39],"supporting":[41],"analysis":[42,68,83],"on":[43,132,147],"these":[44],"large,":[45],"heterogeneous,":[46],"evolving":[48],"data":[49,80,92,99,109,111,128,134,152],"sets.":[50],"\u201cdata":[53],"science\u201d":[54],"refers":[55],"statistical,":[58],"technical,":[59],"domain-specific":[61],"knowledge":[62],"required":[63],"ensure":[65],"that":[66],"is":[69],"done":[70],"properly.":[71],"Techniques":[72],"for":[73,78,125,143,151],"managing":[74],"some":[75],"common":[76],"causes":[77,124],"bad":[79],"invalid":[82,118],"been":[85],"used":[86],"other":[88],"areas,":[89],"such":[90],"as":[91],"warehousing":[93,153],"distributed":[95,155],"database.":[96],"However,":[97],"big":[98,108,127],"face":[101],"special":[102],"challenges":[103],"when":[104],"trying":[105],"combine":[107],"science":[112],"without":[113],"producing":[114],"inaccurate,":[115],"misleading,":[116],"or":[117],"results.":[119],"This":[120],"paper":[121],"discusses":[122],"potential":[123],"\u201cbad":[126],"science\u201d,":[129],"focusing":[130],"primarily":[131],"quality":[135],"input":[138],"data,":[139],"suggests":[141],"methods":[142],"minimizing":[144],"them":[145],"based":[146],"techniques":[148],"originally":[149],"developed":[150],"database":[156],"projects.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}