{"id":"https://openalex.org/W4412956540","doi":"https://doi.org/10.3390/info16080661","title":"Ambiguities, Built-In Biases, and Flaws in Big Data Insight Extraction","display_name":"Ambiguities, Built-In Biases, and Flaws in Big Data Insight Extraction","publication_year":2025,"publication_date":"2025-08-02","ids":{"openalex":"https://openalex.org/W4412956540","doi":"https://doi.org/10.3390/info16080661"},"language":"en","primary_location":{"id":"doi:10.3390/info16080661","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080661","pdf_url":"https://www.mdpi.com/2078-2489/16/8/661/pdf?version=1754277440","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/8/661/pdf?version=1754277440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062833990","display_name":"Serge Galam","orcid":"https://orcid.org/0000-0002-9003-5420"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210116867","display_name":"Centre de Recherches Politiques de Sciences Po","ror":"https://ror.org/0266y7j75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I205092303","https://openalex.org/I4210116867","https://openalex.org/I4210150854"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Serge Galam","raw_affiliation_strings":["CEVIPOF \u2014Centre for Political Research, SciencesPo and CNRS, 1, Place Saint-Thomas d\u2019Aquin, 75007 Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-9003-5420","affiliations":[{"raw_affiliation_string":"CEVIPOF \u2014Centre for Political Research, SciencesPo and CNRS, 1, Place Saint-Thomas d\u2019Aquin, 75007 Paris, France","institution_ids":["https://openalex.org/I4210116867","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062833990"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210116867"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.9109,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86516052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"16","issue":"8","first_page":"661","last_page":"661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6377244591712952},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5107010006904602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.471745103597641},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4391281008720398},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28275907039642334},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.15719610452651978},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.13909953832626343}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6377244591712952},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5107010006904602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.471745103597641},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4391281008720398},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28275907039642334},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.15719610452651978},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.13909953832626343}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16080661","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080661","pdf_url":"https://www.mdpi.com/2078-2489/16/8/661/pdf?version=1754277440","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:04087b8685d74859832f1b1a877b3cd0","is_oa":true,"landing_page_url":"https://doaj.org/article/04087b8685d74859832f1b1a877b3cd0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 8, p 661 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16080661","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080661","pdf_url":"https://www.mdpi.com/2078-2489/16/8/661/pdf?version=1754277440","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412956540.pdf","grobid_xml":"https://content.openalex.org/works/W4412956540.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1597192178","https://openalex.org/W2187089797","https://openalex.org/W2232848979","https://openalex.org/W2295124130","https://openalex.org/W2338072381","https://openalex.org/W2556218092","https://openalex.org/W3084113925","https://openalex.org/W3165945089","https://openalex.org/W4224326051","https://openalex.org/W4313302550","https://openalex.org/W4316468049","https://openalex.org/W4317103806","https://openalex.org/W4361287584","https://openalex.org/W4388761911","https://openalex.org/W4391426767","https://openalex.org/W4391917763","https://openalex.org/W4393217811","https://openalex.org/W4399170978","https://openalex.org/W4400341567","https://openalex.org/W4400776906","https://openalex.org/W4405736597","https://openalex.org/W4408339624","https://openalex.org/W6718991148","https://openalex.org/W6876233187","https://openalex.org/W7056365848"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2731626691","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084"],"abstract_inverted_index":{"I":[0,93],"address":[1],"the":[2,60,63,83,87,120,123,127,141,235,242],"challenge":[3],"of":[4,26,89,126,129,209,264],"extracting":[5],"reliable":[6],"insights":[7],"from":[8,86,157],"large":[9],"datasets":[10],"using":[11],"a":[12,56,73,95,115,132,160,169,185,206,255,261],"simplified":[13],"model":[14,24],"that":[15,80,140],"illustrates":[16],"how":[17,225],"hierarchical":[18,96,270],"classification":[19,271],"can":[20],"distort":[21],"outcomes.":[22,202],"The":[23],"consists":[25],"discrete":[27],"pixels":[28,130],"labeled":[29,66],"red,":[30],"blue,":[31],"or":[32,44],"white.":[33],"Red":[34],"and":[35,107,180],"blue":[36],"indicate":[37],"distinct":[38],"properties,":[39],"while":[40],"white":[41,145,148],"represents":[42,122],"unclassified":[43],"ambiguous":[45],"data.":[46],"A":[47],"macro-color":[48],"is":[49,65,91,215,228],"assigned":[50],"only":[51,218],"if":[52],"one":[53],"color":[54,121,170],"holds":[55],"strict":[57],"majority":[58,111],"among":[59],"pixels.":[61],"Otherwise,":[62],"aggregate":[64],"white,":[67],"reflecting":[68],"uncertainty.":[69],"This":[70,203],"setup":[71],"mimics":[72],"percolation":[74],"threshold":[75],"at":[76],"fifty":[77],"percent.":[78],"Assuming":[79],"directly":[81],"accessing":[82],"various":[84],"proportions":[85],"data":[88,211,220,243],"colors":[90],"infeasible,":[92],"implement":[94],"coarse-graining":[97],"procedure.":[98],"Elements":[99],"(first":[100],"pixels,":[101,149],"then":[102],"aggregates)":[103],"are":[104,198,238],"recursively":[105],"grouped":[106],"reclassified":[108],"via":[109],"local":[110,175,196,226,250],"rules,":[112],"ultimately":[113],"producing":[114],"single":[116],"super-aggregate":[117],"for":[118],"which":[119,150],"inferred":[124],"macro-property":[125],"collection":[128],"as":[131],"whole.":[133],"Analytical":[134],"results":[135],"supported":[136],"by":[137,219,224],"simulations":[138],"show":[139],"process":[142],"introduces":[143],"additional":[144],"aggregates":[146],"beyond":[147],"could":[151],"be":[152],"present":[153],"initially;":[154],"these":[155,258],"arise":[156],"groups":[158],"lacking":[159],"clear":[161],"majority,":[162],"requiring":[163],"arbitrary":[164],"symmetry-breaking":[165],"decisions":[166],"to":[167,171,200,241,245],"attribute":[168],"them.":[172],"While":[173],"each":[174],"resolution":[176],"may":[177],"appear":[178],"minor":[179],"inconsequential,":[181],"their":[182],"repetitions":[183],"introduce":[184],"growing":[186],"systematic":[187],"bias.":[188],"Even":[189],"with":[190],"complete":[191],"data,":[192],"unavoidable":[193],"asymmetries":[194],"in":[195,231,267],"rules":[197],"shown":[199],"skew":[201],"study":[204],"highlights":[205],"critical":[207],"limitation":[208],"recursive":[210],"reduction.":[212],"Insight":[213],"extraction":[214],"shaped":[216],"not":[217,239],"quality":[221],"but":[222,244],"also":[223],"ambiguity":[227],"handled,":[229],"resulting":[230],"built-in":[232],"biases.":[233],"Thus,":[234],"related":[236],"flaws":[237,266],"due":[240],"structural":[246],"choices":[247],"made":[248],"during":[249],"aggregations.":[251],"Although":[252],"based":[253],"on":[254],"simple":[256],"model,":[257],"findings":[259],"expose":[260],"high":[262],"likelihood":[263],"inherent":[265],"widely":[268],"used":[269],"techniques.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}