{"id":"https://openalex.org/W2584982695","doi":"https://doi.org/10.1145/3018661.3022750","title":"Scalable Text Analysis","display_name":"Scalable Text Analysis","publication_year":2017,"publication_date":"2017-02-02","ids":{"openalex":"https://openalex.org/W2584982695","doi":"https://doi.org/10.1145/3018661.3022750","mag":"2584982695"},"language":"en","primary_location":{"id":"doi:10.1145/3018661.3022750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3018661.3022750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM International Conference on Web Search and Data Mining","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/A5036741606","display_name":"Zijun Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zijun Xue","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036741606"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01123224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"835","last_page":"835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.8798134326934814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8540022373199463},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8299713730812073},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7316865921020508},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5679850578308105},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4868606925010681},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4589579701423645},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4536546766757965},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4373414218425751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333556294441223},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39597535133361816},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3558833599090576},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0739881694316864},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.06720438599586487}],"concepts":[{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8798134326934814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540022373199463},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8299713730812073},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7316865921020508},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5679850578308105},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4868606925010681},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4589579701423645},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4536546766757965},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4373414218425751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333556294441223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39597535133361816},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3558833599090576},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0739881694316864},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.06720438599586487},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3018661.3022750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3018661.3022750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2041517243","https://openalex.org/W2146341620","https://openalex.org/W2150731624"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Latent":[0],"Dirichlet":[1],"Allocation":[2],"(LDA)":[3],"is":[4,26],"an":[5],"extremely":[6],"popular":[7],"probabilistic":[8],"topic":[9],"model":[10],"used":[11],"for":[12],"a":[13,41,50],"diverse":[14],"class":[15],"of":[16,24,31,73,87,104,128],"appications.":[17],"While":[18],"highly":[19],"effective,":[20],"one":[21],"important":[22],"limitation":[23],"LDA":[25,53],"the":[27,57,71,74,88],"high":[28],"memory":[29,82],"footprint":[30,67],"its":[32,65],"inferencing":[33,89],"algorithm,":[34],"making":[35],"it":[36],"difficult":[37],"to":[38,40,63,79,98,123],"scale":[39],"large":[42],"dataset.":[43],"In":[44],"my":[45],"thesis,":[46],"I":[47],"propose":[48],"sdLDA,":[49],"highly-scalable":[51],"disk-based":[52],"that":[54,95,100],"(1)":[55],"leverages":[56],"plentiful":[58],"space":[59],"available":[60],"in":[61,126],"disk":[62],"reduce":[64],"main-memory":[66],"and":[68,84],"(2)":[69],"preserves":[70],"sparsity":[72],"extracted":[75],"topics":[76],"during":[77],"sampling":[78,85],"improve":[80],"both":[81],"efficiency":[83],"complexity":[86],"algorithm.":[90],"Our":[91],"extensive":[92],"experiments":[93],"show":[94],"sdLDA":[96,115],"scales":[97],"datasets":[99],"are":[101],"two":[102],"orders":[103],"magnitude":[105],"larger":[106],"than":[107],"what":[108],"existing":[109],"main-memory-based":[110,124],"algorithms":[111],"can":[112],"handle.":[113],"Furthermore,":[114],"exhibits":[116],"similar":[117],"(or":[118],"even":[119],"better)":[120],"performance":[121],"compared":[122],"LDAs":[125],"terms":[127],"running":[129],"time.":[130]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}