{"id":"https://openalex.org/W2584524946","doi":"https://doi.org/10.1109/bigdata.2016.7841060","title":"Efficient natural language pre-processing for analyzing large data sets","display_name":"Efficient natural language pre-processing for analyzing large data sets","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584524946","doi":"https://doi.org/10.1109/bigdata.2016.7841060","mag":"2584524946"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7841060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5048761877","display_name":"Billal Belainine","orcid":"https://orcid.org/0000-0002-3261-5697"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Belainine Billal","raw_affiliation_strings":["Department of Computer Science, University of Quebec in Montreal, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Quebec in Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038673364","display_name":"Alexsandro Fonseca","orcid":null},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexsandro Fonseca","raw_affiliation_strings":["Department of Computer Science, University of Quebec in Montreal, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Quebec in Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030866856","display_name":"Fatiha Sadat","orcid":"https://orcid.org/0000-0002-9292-722X"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fatiha Sadat","raw_affiliation_strings":["Department of Computer Science, University of Quebec in Montreal, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Quebec in Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048761877"],"corresponding_institution_ids":["https://openalex.org/I159129438"],"apc_list":null,"apc_paid":null,"fwci":2.1424,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91121317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3864","last_page":"3871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9951000213623047,"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/T11719","display_name":"Data Quality and Management","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8567890524864197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7289454340934753},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.726493775844574},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.710547685623169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6696239709854126},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6195389032363892},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6152095198631287},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5309602618217468},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4569329619407654},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4293499290943146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.347700834274292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567890524864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7289454340934753},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.726493775844574},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.710547685623169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6696239709854126},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6195389032363892},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6152095198631287},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5309602618217468},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4569329619407654},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4293499290943146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.347700834274292},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7841060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7841060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"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":27,"referenced_works":["https://openalex.org/W10067149","https://openalex.org/W1625504505","https://openalex.org/W1637206244","https://openalex.org/W1817561967","https://openalex.org/W1839863673","https://openalex.org/W2015186536","https://openalex.org/W2016443085","https://openalex.org/W2053968437","https://openalex.org/W2087347434","https://openalex.org/W2089468765","https://openalex.org/W2116235440","https://openalex.org/W2118585731","https://openalex.org/W2126581182","https://openalex.org/W2136480620","https://openalex.org/W2142016317","https://openalex.org/W2142623206","https://openalex.org/W2153635508","https://openalex.org/W2251173601","https://openalex.org/W2267835966","https://openalex.org/W2404028324","https://openalex.org/W2406960794","https://openalex.org/W2436001372","https://openalex.org/W6600381341","https://openalex.org/W6636859864","https://openalex.org/W6677656871","https://openalex.org/W6693772185","https://openalex.org/W6713098295"],"related_works":["https://openalex.org/W2900382651","https://openalex.org/W1981879262","https://openalex.org/W2363417484","https://openalex.org/W4225863708","https://openalex.org/W1480103567","https://openalex.org/W1599970036","https://openalex.org/W1849827364","https://openalex.org/W2786299737","https://openalex.org/W1619002","https://openalex.org/W2977327189"],"abstract_inverted_index":{"The":[0],"phenomenon":[1],"of":[2,84,107,112,117,124,141],"big":[3],"data":[4,64],"is":[5,97],"described":[6],"using":[7,109,130],"five":[8],"Vs:":[9],"Volume,":[10],"Variety,":[11],"Velocity,":[12],"Variability":[13],"and":[14,24,29,37,50,65,69,92,104,114],"Veracity.":[15],"In":[16,73],"this":[17,74,131],"paper,":[18,75],"we":[19,76],"are":[20,44],"interested":[21],"by":[22],"analyzing":[23],"pre-processing":[25,79],"tweets":[26,82,108],"for":[27,81],"NLP":[28,68],"machine":[30,35,70],"learning":[31,71],"applications":[32],"such":[33,63],"as":[34,46],"translation":[36],"classification.":[38],"Collected":[39],"contents":[40],"from":[41,62],"Twitter":[42],"(tweets)":[43],"considered":[45],"unstructured,":[47],"highly":[48],"noisy":[49],"short":[51],"(140":[52],"characters)":[53],"texts.":[54],"Overcoming":[55],"these":[56],"complex":[57],"challenges":[58],"will":[59],"help":[60],"learn":[61],"apply":[66],"traditional":[67],"techniques.":[72],"propose":[77],"a":[78],"pipeline":[80],"consisting":[83],"filtering":[85],"part-of-speech,":[86],"named":[87],"entities":[88],"recognition,":[89],"hashtag":[90],"segmentation":[91],"disambiguation.":[93],"Our":[94],"proposed":[95,132],"approach":[96],"also":[98],"based":[99],"on":[100,121],"the":[101,115,122,139,142],"graph":[102],"theory":[103],"group":[105],"words":[106],"semantic":[110],"relations":[111],"WordNet":[113],"idea":[116],"connected":[118],"components.":[119],"Evaluations":[120],"task":[123],"classification":[125,143],"showed":[126],"promising":[127],"results":[128],"when":[129],"preprocessing":[133],"pipeline,":[134],"with":[135],"an":[136],"increase":[137],"in":[138],"accuracy":[140],"up":[144],"to":[145],"87.6%.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}