{"id":"https://openalex.org/W3184889865","doi":"https://doi.org/10.1145/3459104.3459198","title":"Real-time Text Stream Processing: A Dynamic and Distributed NLP Pipeline","display_name":"Real-time Text Stream Processing: A Dynamic and Distributed NLP Pipeline","publication_year":2021,"publication_date":"2021-02-19","ids":{"openalex":"https://openalex.org/W3184889865","doi":"https://doi.org/10.1145/3459104.3459198","mag":"3184889865"},"language":"en","primary_location":{"id":"doi:10.1145/3459104.3459198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459104.3459198","pdf_url":null,"source":{"id":"https://openalex.org/S4306498858","display_name":"2021 International Symposium on Electrical, Electronics and Information Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Electrical, Electronics and Information Engineering","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/A5019244064","display_name":"Mohammad Arshi Saloot","orcid":"https://orcid.org/0000-0003-0819-6530"},"institutions":[{"id":"https://openalex.org/I891303086","display_name":"MIMOS (Malaysia)","ror":"https://ror.org/01k94e681","country_code":"MY","type":"company","lineage":["https://openalex.org/I891303086"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Mohammad Arshi Saloot","raw_affiliation_strings":["MIMOS Berhad, Malaysia"],"affiliations":[{"raw_affiliation_string":"MIMOS Berhad, Malaysia","institution_ids":["https://openalex.org/I891303086"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033848427","display_name":"Duc Nghia Pham","orcid":"https://orcid.org/0009-0001-8985-017X"},"institutions":[{"id":"https://openalex.org/I891303086","display_name":"MIMOS (Malaysia)","ror":"https://ror.org/01k94e681","country_code":"MY","type":"company","lineage":["https://openalex.org/I891303086"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Duc Nghia Pham","raw_affiliation_strings":["MIMOS Berhad, Malaysia"],"affiliations":[{"raw_affiliation_string":"MIMOS Berhad, Malaysia","institution_ids":["https://openalex.org/I891303086"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019244064"],"corresponding_institution_ids":["https://openalex.org/I891303086"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72372098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"575","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9983999729156494,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.834805965423584},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.7204383611679077},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6906135082244873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262442469596863},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5573877096176147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5439538955688477},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4753287136554718},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.45696040987968445},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29156363010406494},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11236488819122314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834805965423584},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.7204383611679077},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6906135082244873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262442469596863},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5573877096176147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5439538955688477},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4753287136554718},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.45696040987968445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29156363010406494},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11236488819122314},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459104.3459198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459104.3459198","pdf_url":null,"source":{"id":"https://openalex.org/S4306498858","display_name":"2021 International Symposium on Electrical, Electronics and Information Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Electrical, Electronics and Information Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W192446467","https://openalex.org/W1875470695","https://openalex.org/W1992777957","https://openalex.org/W2123442489","https://openalex.org/W2143017621","https://openalex.org/W2185357164","https://openalex.org/W2251991755","https://openalex.org/W2252147815","https://openalex.org/W2493916176","https://openalex.org/W2531621976","https://openalex.org/W2534179372","https://openalex.org/W2542459869","https://openalex.org/W2728951081","https://openalex.org/W2753910905","https://openalex.org/W2783913044","https://openalex.org/W2901263649","https://openalex.org/W2903332489","https://openalex.org/W2915025126","https://openalex.org/W2949006873","https://openalex.org/W2963626623","https://openalex.org/W2979325626","https://openalex.org/W6639944454","https://openalex.org/W6719819555","https://openalex.org/W6732077288"],"related_works":["https://openalex.org/W4317418912","https://openalex.org/W3215034299","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W2772504652","https://openalex.org/W3155891479","https://openalex.org/W3029351463"],"abstract_inverted_index":{"In":[0,32],"recent":[1],"years,":[2],"the":[3,36,107,110,138],"need":[4],"for":[5,125],"flexible":[6],"and":[7,45,60,78,122,128,144],"instant":[8],"Natural":[9],"Language":[10],"Processing":[11],"(NLP)":[12],"pipelines":[13],"becomes":[14],"more":[15],"crucial.":[16],"The":[17,91,131],"existence":[18,37],"of":[19,38,42,50,64,88,109,114],"real-time":[20,28,72],"data":[21],"sources,":[22],"such":[23],"as":[24],"Twitter,":[25],"necessitates":[26],"using":[27],"text":[29],"analysis":[30],"platforms.":[31],"addition,":[33],"due":[34],"to":[35,58,81,95,99,118],"a":[39,48,53,71,112],"wide":[40],"range":[41],"NLP":[43,66,84,97],"toolkits":[44],"libraries":[46],"in":[47],"variety":[49],"programming":[51,103],"languages,":[52],"streaming":[54],"platform":[55],"is":[56],"required":[57],"combine":[59],"integrate":[61],"different":[62,83,102],"modules":[63,98,124],"various":[65],"toolkits.":[67],"This":[68],"study":[69],"proposes":[70],"architecture":[73,92],"that":[74,134],"uses":[75],"Apache":[76,79,135],"Storm":[77,136],"Kafka":[80],"apply":[82],"tasks":[85],"on":[86],"streams":[87],"textual":[89],"data.":[90],"allows":[93],"developers":[94],"inject":[96],"it":[100],"via":[101],"languages.":[104,130],"To":[105],"compare":[106],"performance":[108],"architecture,":[111],"series":[113],"experiments":[115],"are":[116],"conducted":[117],"handle":[119],"OpenNLP,":[120],"Fasttext,":[121],"SpaCy":[123],"Bahasa":[126],"Malaysia":[127],"English":[129],"result":[132],"shows":[133],"achieved":[137],"lowest":[139],"latency,":[140],"compared":[141],"with":[142],"Trident":[143],"baseline":[145],"experiments.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
