{"id":"https://openalex.org/W4287330812","doi":"https://doi.org/10.48550/arxiv.2102.04141","title":"Empowering Investigative Journalism with Graph-based Heterogeneous Data Management","display_name":"Empowering Investigative Journalism with Graph-based Heterogeneous Data Management","publication_year":2021,"publication_date":"2021-02-08","ids":{"openalex":"https://openalex.org/W4287330812","doi":"https://doi.org/10.48550/arxiv.2102.04141"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2102.04141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04141","pdf_url":"https://arxiv.org/pdf/2102.04141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.04141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086242059","display_name":"Angelos-Christos G. Anadiotis","orcid":"https://orcid.org/0000-0001-8101-6044","observed_orcids":["https://orcid.org/0000-0001-8101-6044"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Anadiotis, Angelos-Christos","raw_affiliation_strings":["\u00c9cole Polytechnique , IPP & EPFL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique , IPP & EPFL","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210145102","https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045913576","display_name":"Oana Balalau","orcid":"https://orcid.org/0000-0003-1469-3664","observed_orcids":["https://orcid.org/0000-0003-1469-3664"]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Balalau, Oana","raw_affiliation_strings":["Inria & IPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & IPP","institution_ids":["https://openalex.org/I4210139716","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008843803","display_name":"Th\u00e9o Bouganim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Bouganim, Theo","raw_affiliation_strings":["Inria & IPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & IPP","institution_ids":["https://openalex.org/I4210139716","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019218627","display_name":"Francesco Chimienti","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Chimienti, Francesco","raw_affiliation_strings":["Inria & IPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & IPP","institution_ids":["https://openalex.org/I4210139716","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010625393","display_name":"H\u00e9l\u00e9na Galhardas","orcid":"https://orcid.org/0000-0002-9330-3910","observed_orcids":["https://orcid.org/0000-0002-9330-3910"]},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Galhardas, Helena","raw_affiliation_strings":["INESC-ID & IST , Univ. Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INESC-ID & IST , Univ. Lisboa","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077734209","display_name":"Mhd Yamen Haddad","orcid":"https://orcid.org/0000-0002-2206-1328","observed_orcids":["https://orcid.org/0000-0002-2206-1328"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haddad, Mhd Yamen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023940852","display_name":"St\u00e9phane Horel","orcid":"https://orcid.org/0009-0007-3286-4718","observed_orcids":["https://orcid.org/0009-0007-3286-4718"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horel, Stephane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056968239","display_name":"Ioana Manolescu","orcid":"https://orcid.org/0000-0002-0425-2462","observed_orcids":["https://orcid.org/0000-0002-0425-2462"]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Manolescu, Ioana","raw_affiliation_strings":["Inria & IPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & IPP","institution_ids":["https://openalex.org/I4210139716","https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001893454","display_name":"Youssr Youssef","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139716","display_name":"Max Planck Institute for Plasma Physics","ror":"https://ror.org/03taest98","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210139716"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Youssef, Youssr","raw_affiliation_strings":["Inria & IPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & IPP","institution_ids":["https://openalex.org/I4210139716","https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.2890999913215637,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.2890999913215637,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.1907999962568283,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.14000000059604645,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/investigative-journalism","display_name":"investigative journalism","score":0.9990000128746033},{"id":"https://openalex.org/keywords/keyword-search","display_name":"keyword search","score":0.699999988079071},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.7300000190734863},{"id":"https://openalex.org/keywords/conflict-of-interest","display_name":"conflicts of interest","score":0.7739999890327454},{"id":"https://openalex.org/keywords/parallel-search","display_name":"parallel search","score":0.6169999837875366},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922459840774536},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6755275726318359},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6709509491920471},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6031785607337952},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4934188425540924},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.4537799656391144},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.434179425239563},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4187781512737274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4155169129371643},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4072590470314026},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1277625560760498},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2102.04141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04141","pdf_url":"https://arxiv.org/pdf/2102.04141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03337650v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03337650v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bulletin of the Technical Committee on Data Engineering, In press","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2102.04141","doi":"https://doi.org/10.48550/arxiv.2102.04141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.04141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.04141","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04141","pdf_url":"https://arxiv.org/pdf/2102.04141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287330812.pdf","grobid_xml":"https://content.openalex.org/works/W4287330812.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W122713538","https://openalex.org/W1570477871","https://openalex.org/W1870305865","https://openalex.org/W1969621019","https://openalex.org/W1973828215","https://openalex.org/W1981585544","https://openalex.org/W1981943579","https://openalex.org/W2019876129","https://openalex.org/W2053076698","https://openalex.org/W2055497547","https://openalex.org/W2085494605","https://openalex.org/W2088499566","https://openalex.org/W2152907584","https://openalex.org/W2162833734","https://openalex.org/W2168827908","https://openalex.org/W2180737804","https://openalex.org/W2260616469","https://openalex.org/W2406352087","https://openalex.org/W2621373082","https://openalex.org/W2739409954","https://openalex.org/W2795089200","https://openalex.org/W2795302121","https://openalex.org/W2884952043","https://openalex.org/W2922521871","https://openalex.org/W2944730199","https://openalex.org/W2950422288","https://openalex.org/W3031051334","https://openalex.org/W3082162291","https://openalex.org/W3082867112","https://openalex.org/W3084126024","https://openalex.org/W3180107114","https://openalex.org/W4286447301"],"related_works":["https://openalex.org/W3209474564","https://openalex.org/W4285607768","https://openalex.org/W3180107114","https://openalex.org/W2884952043","https://openalex.org/W3084126024","https://openalex.org/W4399196736","https://openalex.org/W3042782640","https://openalex.org/W3004836124","https://openalex.org/W1018140401","https://openalex.org/W4386768625"],"abstract_inverted_index":{"Investigative":[0],"Journalism":[1],"(IJ,":[2],"in":[3,126],"short)":[4],"is":[5,88,165],"staple":[6],"of":[7,19,34,49,71,98,109,124,176,195],"modern,":[8],"democratic":[9],"societies.":[10],"IJ":[11,120,189],"often":[12],"necessitates":[13],"working":[14],"with":[15],"large,":[16],"dynamic":[17],"sets":[18],"heterogeneous,":[20],"schema-less":[21],"data":[22,36,191],"sources,":[23],"which":[24,173],"can":[25,64],"be":[26],"structured,":[27],"semi-structured,":[28],"or":[29],"textual,":[30],"limiting":[31],"the":[32,67,91,96,110,127,143,154,160,163,187,193],"applicability":[33],"classical":[35],"integration":[37],"approaches.":[38],"In":[39,113],"prior":[40],"work,":[41,115],"we":[42,116,131,138],"have":[43],"developed":[44],"ConnectionLens,":[45],"a":[46,54,99,166],"system":[47],"capable":[48],"integrating":[50],"such":[51],"sources":[52],"into":[53],"single":[55],"heterogeneous":[56],"graph,":[57,161],"leveraging":[58],"Information":[59],"Extraction":[60],"(IE)":[61],"techniques;":[62],"users":[63],"then":[65],"query":[66,75],"graph":[68,92],"by":[69,90,95,147],"means":[70],"keywords,":[72],"and":[73,77,94,130],"explore":[74],"results":[76],"their":[78],"neighborhood":[79],"using":[80],"an":[81,118],"interactive":[82],"GUI.":[83],"Our":[84,183],"keyword":[85,170],"search":[86,111,171],"problem":[87],"complicated":[89],"heterogeneity,":[93],"lack":[97],"result":[100],"score":[101],"function":[102],"that":[103],"would":[104],"allow":[105],"to":[106,152],"prune":[107],"some":[108],"space.":[112],"this":[114,148],"describe":[117],"actual":[119],"application":[121,190],"studying":[122],"conflicts":[123],"interest":[125],"biomedical":[128],"domain,":[129],"show":[132],"how":[133],"ConnectionLens":[134],"supports":[135],"it.":[136],"Then,":[137],"present":[139],"novel":[140],"techniques":[141],"addressing":[142],"scalability":[144],"challenges":[145],"raised":[146],"application:":[149],"one":[150],"allows":[151],"reduce":[153],"significant":[155],"IE":[156],"costs":[157],"while":[158,162],"building":[159],"other":[164],"novel,":[167],"parallel,":[168],"in-memory":[169],"engine,":[172],"achieves":[174],"orders":[175],"magnitude":[177],"speed-up":[178],"over":[179],"our":[180,196],"previous":[181],"engine.":[182],"experimental":[184],"study":[185],"on":[186],"real-world":[188],"confirms":[192],"benefits":[194],"contributions.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-25T00:00:00"}
