{"id":"https://openalex.org/W2782695809","doi":"https://doi.org/10.1109/bigdata.2017.8258559","title":"EOS: A multilingual text archive of international newspaper &amp; blog articles","display_name":"EOS: A multilingual text archive of international newspaper &amp; blog articles","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2782695809","doi":"https://doi.org/10.1109/bigdata.2017.8258559","mag":"2782695809"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5005384315","display_name":"Lisa Singh","orcid":"https://orcid.org/0000-0002-8300-2970"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lisa Singh","raw_affiliation_strings":["Department of Computer Science, Georgetown University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086838434","display_name":"Raghu Pemmaraju","orcid":"https://orcid.org/0000-0003-2968-6053"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghu Pemmaraju","raw_affiliation_strings":["University Information Systems, Georgetown University"],"affiliations":[{"raw_affiliation_string":"University Information Systems, Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005384315"],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":null,"apc_paid":null,"fwci":0.9673,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8406298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"4835","last_page":"4837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9865999817848206,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9865000247955322,"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/newspaper","display_name":"Newspaper","score":0.9238364696502686},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6902744770050049},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6278119087219238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5935556888580322},{"id":"https://openalex.org/keywords/internet-portal","display_name":"Internet portal","score":0.5244351029396057},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4429529905319214},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33536213636398315},{"id":"https://openalex.org/keywords/media-studies","display_name":"Media studies","score":0.18280932307243347},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11448386311531067},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.10081496834754944}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.9238364696502686},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6902744770050049},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6278119087219238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5935556888580322},{"id":"https://openalex.org/C3019770801","wikidata":"https://www.wikidata.org/wiki/Q186165","display_name":"Internet portal","level":3,"score":0.5244351029396057},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4429529905319214},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33536213636398315},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.18280932307243347},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11448386311531067},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.10081496834754944},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"},{"id":"https://openalex.org/F4320310223","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1978295781","https://openalex.org/W2149787734","https://openalex.org/W2160159983","https://openalex.org/W2296880476","https://openalex.org/W2464913760","https://openalex.org/W2561889001","https://openalex.org/W2571826164","https://openalex.org/W2769332040","https://openalex.org/W2914756073","https://openalex.org/W6697630386"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2996664812","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W644339423","https://openalex.org/W2386525189"],"abstract_inverted_index":{"The":[0],"Expandable":[1],"Open":[2],"Source":[3],"(EOS)":[4],"database":[5],"maintains":[6],"an":[7],"archive":[8,22],"of":[9,44,48],"Internet":[10],"accessible":[11],"newspaper":[12],"and":[13,28,51,65],"blog":[14],"articles":[15,27,34],"from":[16],"across":[17],"the":[18,21,42],"world.":[19],"Today,":[20],"contains":[23],"over":[24],"700":[25],"million":[26],"is":[29],"growing":[30],"by":[31],"approximately":[32],"100,000":[33],"each":[35],"day.":[36],"In":[37],"this":[38,63],"work,":[39],"we":[40],"describe":[41],"components":[43],"EOS,":[45],"our":[46],"community":[47],"data":[49,52],"users":[50],"providers,":[53],"some":[54],"real":[55],"world":[56],"use":[57],"cases,":[58],"challenges":[59],"associated":[60],"with":[61],"maintaining":[62],"archive,":[64],"a":[66,72],"vision":[67],"for":[68],"its":[69],"future":[70],"as":[71],"text":[73],"analytic":[74],"portal.":[75]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
