{"id":"https://openalex.org/W2047348798","doi":"https://doi.org/10.1145/2213836.2213970","title":"Towards scalable summarization and visualization of large text corpora (abstract only)","display_name":"Towards scalable summarization and visualization of large text corpora (abstract only)","publication_year":2012,"publication_date":"2012-05-20","ids":{"openalex":"https://openalex.org/W2047348798","doi":"https://doi.org/10.1145/2213836.2213970","mag":"2047348798"},"language":"en","primary_location":{"id":"doi:10.1145/2213836.2213970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of 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/A5075522958","display_name":"Tyler Sliwkanich","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tyler Sliwkanich","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080914334","display_name":"Douglas Schneider","orcid":"https://orcid.org/0000-0003-0511-8326"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Douglas Schneider","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103615366","display_name":"Aaron Yong","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aaron Yong","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024780391","display_name":"Mitchell Home","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mitchell Home","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061046432","display_name":"Denilson Barbosa","orcid":"https://orcid.org/0000-0002-6104-1987"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Denilson Barbosa","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.2776,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57967393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9006999731063843,"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/computer-science","display_name":"Computer science","score":0.8578831553459167},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8006933331489563},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.658794641494751},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5997323989868164},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.4890502393245697},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4876605272293091},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4575537443161011},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4489728808403015},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.4326377511024475},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4200286865234375},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3076346218585968},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1968609094619751},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19215932488441467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17723524570465088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578831553459167},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8006933331489563},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.658794641494751},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5997323989868164},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.4890502393245697},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4876605272293091},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4575537443161011},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4489728808403015},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.4326377511024475},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4200286865234375},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3076346218585968},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1968609094619751},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19215932488441467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17723524570465088}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2213836.2213970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W3089119258","https://openalex.org/W2923327995","https://openalex.org/W2518340158","https://openalex.org/W3147331693","https://openalex.org/W349054995","https://openalex.org/W2086537700","https://openalex.org/W2997849137","https://openalex.org/W2366403280"],"abstract_inverted_index":{"Society":[0],"is":[1,44,211,226],"awash":[2],"with":[3,178,236],"problems":[4],"requiring":[5],"the":[6,45,79,162,169,176,186,217,248,286,298,315,338],"analysis":[7],"of":[8,11,20,47,59,168,216,232,250,267,300],"vast":[9],"quantities":[10,58],"text":[12,39,144],"and":[13,33,50,69,86,94,141,164,171,180,221,254,276],"data.":[14,330],"From":[15],"detecting":[16],"flu":[17],"trends":[18],"out":[19],"twitter":[21],"conversations":[22],"to":[23,37,53,89,132,139,154,262,280,285,297,313,335],"finding":[24],"scholarly":[25],"works":[26],"answering":[27],"specific":[28],"questions,":[29],"we":[30,147,193,241,245,320,332],"rely":[31,309],"more":[32,34,115],"on":[35,102,213,310,328],"computers":[36],"process":[38,295],"for":[40,73,137,152,341],"us.":[41],"Text":[42],"analytics":[43],"application":[46],"computational,":[48],"mathematical,":[49],"statistical":[51],"models":[52],"derive":[54],"information":[55,96,183],"from":[56,98,185],"large":[57,74,143,265],"data":[60,210,269,316],"coming":[61],"primarily":[62],"as":[63,78,188,205,228],"text.":[64,99],"Our":[65],"project":[66],"provides":[67,175,273],"fast":[68],"effective":[70],"text-analytics":[71],"tools":[72,131],"document":[75],"collections,":[76],"such":[77],"blogosphere.":[80],"We":[81,100,122],"use":[82,322,333],"natural":[83],"language":[84],"processing":[85],"database":[87,219,301],"techniques":[88],"extract,":[90],"collect,":[91],"analyze,":[92],"visualize,":[93],"archive":[95],"extracted":[97,209],"focus":[101],"discovering":[103],"relationships":[104],"between":[105],"entities":[106,170],"(people,":[107],"places,":[108],"organizations,":[109],"etc.)":[110],"mentioned":[111],"in":[112,317],"one":[113],"or":[114,119],"sources":[116],"(blog":[117],"posts":[118],"news":[120],"articles).":[121],"built":[123],"a":[124,134,189,214,274,294,323],"custom":[125],"solution":[126],"using":[127,270],"mostly":[128],"off-the-shelf,":[129],"open-source":[130],"provide":[133,148],"scalable":[135],"platform":[136],"users":[138,153],"search":[140,160],"analyze":[142],"corpora.":[145],"Currently,":[146],"two":[149],"main":[150],"outlets":[151],"discover":[155],"these":[156],"relations:":[157],"(1)":[158],"full-text":[159],"over":[161],"documents":[163],"(2)":[165],"graph":[166,307,325],"visualizations":[167,308],"their":[172],"relationships.":[173],"This":[174,224],"user":[177],"succinct":[179],"easily":[181,195],"digestible":[182],"gleaned":[184],"corpus":[187],"whole.":[190],"For":[191],"example,":[192],"can":[194,246],"pose":[196],"queries":[197,342],"like":[198],"which":[199,259],"companies":[200],"were":[201],"bought":[202],"by":[203,293,304],"Google?":[204],"entity:google":[206],"relation:bought.":[207],"The":[208,306],"stored":[212],"combination":[215,225],"noSQL":[218],"CouchDB":[220],"Apache's":[222],"Lucene.":[223],"justified":[227],"our":[229],"work-flow":[230],"consists":[231],"offline":[233],"batch":[234],"insertions":[235],"almost":[237],"no":[238],"updates.":[239],"Because":[240],"support":[242],"specialized":[243],"queries,":[244],"forgo":[247],"flexibility":[249],"traditional":[251],"SQL":[252],"solutions":[253],"materialize":[255],"all":[256],"necessary":[257],"indices,":[258],"are":[260,291],"used":[261],"quickly":[263],"query":[264,278],"amounts":[266],"de-normalized":[268],"MapReduce.":[271],"Lucene":[272],"flexible":[275],"powerful":[277],"syntax":[279],"yield":[281],"relevant":[282],"ranked":[283],"results":[284],"user.":[287],"Moreover,":[288],"its":[289],"indices":[290],"synchronized":[292],"subscribed":[296],"list":[299],"changes":[302],"published":[303],"CouchDB.":[305],"CouchDB's":[311],"ability":[312],"export":[314],"any":[318],"format:":[319],"currently":[321],"customized":[324],"visualization":[326],"relying":[327],"XML":[329],"Finally,":[331],"memcached":[334],"further":[336],"improve":[337],"performance,":[339],"especially":[340],"involving":[343],"popular":[344],"entities.":[345]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}