{"id":"https://openalex.org/W4386320423","doi":"https://doi.org/10.1109/access.2023.3310818","title":"A Comparative Study on R Packages for Text Mining","display_name":"A Comparative Study on R Packages for Text Mining","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386320423","doi":"https://doi.org/10.1109/access.2023.3310818"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3310818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310818","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10235966.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10235966.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031598229","display_name":"Carlos J. Hell\u00edn","orcid":"https://orcid.org/0000-0002-1576-5466"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Carlos J. Hell\u00edn","raw_affiliation_strings":["Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091983834","display_name":"Adri\u00e1n Valledor","orcid":"https://orcid.org/0000-0002-6899-1336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Valledor","raw_affiliation_strings":["Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039218778","display_name":"Juan J. Cuadrado\u2010Gallego","orcid":"https://orcid.org/0000-0001-8178-5556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan J. Cuadrado-Gallego","raw_affiliation_strings":["Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003197810","display_name":"Abdelhamid Tayebi","orcid":"https://orcid.org/0000-0002-6216-257X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelhamid Tayebi","raw_affiliation_strings":["Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083718621","display_name":"Josefa G\u00f3mez","orcid":"https://orcid.org/0000-0003-0111-8898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josefa G\u00f3mez","raw_affiliation_strings":["Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Alcal&#x00E1;, Alcal&#x00E1; de Henares, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031598229"],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6959,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75935262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"99083","last_page":"99100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9926000237464905,"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":0.8413158655166626},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6024106740951538},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5549507737159729},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5039131045341492},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5005230903625488},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.49496620893478394},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49063506722450256},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4596500098705292},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43791669607162476},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.43689393997192383},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42446091771125793},{"id":"https://openalex.org/keywords/concept-mining","display_name":"Concept mining","score":0.4212349057197571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3251793384552002},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.3223772346973419},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.2169298231601715},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18072840571403503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413158655166626},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6024106740951538},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5549507737159729},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5039131045341492},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5005230903625488},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.49496620893478394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49063506722450256},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4596500098705292},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43791669607162476},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.43689393997192383},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42446091771125793},{"id":"https://openalex.org/C176775163","wikidata":"https://www.wikidata.org/wiki/Q5158396","display_name":"Concept mining","level":4,"score":0.4212349057197571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3251793384552002},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.3223772346973419},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.2169298231601715},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18072840571403503},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3310818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310818","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10235966.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:ebuah.uah.es:10017/63235","is_oa":true,"landing_page_url":"http://hdl.handle.net/10017/63235","pdf_url":"https://ebuah.uah.es/dspace/bitstream/10017/63235/3/Comparative_Hellin_IEEEAccess_2023.pdf","source":{"id":"https://openalex.org/S7407055200","display_name":"e_Buah","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:3d94f1ad6ee048a0abcc907813e53ceb","is_oa":true,"landing_page_url":"https://doaj.org/article/3d94f1ad6ee048a0abcc907813e53ceb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 99083-99100 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3310818","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3310818","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10235966.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2589932926","display_name":null,"funder_award_id":"EPU-INV/2020/004","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G3699213180","display_name":null,"funder_award_id":"Spain","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G6265333667","display_name":null,"funder_award_id":"EPU-INV/2020/004","funder_id":"https://openalex.org/F4320323755","funder_display_name":"Universidad de Alcal\u00e1"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320323755","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386320423.pdf","grobid_xml":"https://content.openalex.org/works/W4386320423.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W38739846","https://openalex.org/W152176684","https://openalex.org/W1488197732","https://openalex.org/W1753361524","https://openalex.org/W1875160599","https://openalex.org/W1973193168","https://openalex.org/W1979076595","https://openalex.org/W1983578042","https://openalex.org/W2002639244","https://openalex.org/W2008495066","https://openalex.org/W2016089260","https://openalex.org/W2037450062","https://openalex.org/W2042670859","https://openalex.org/W2060711947","https://openalex.org/W2091273188","https://openalex.org/W2102451297","https://openalex.org/W2102650424","https://openalex.org/W2114552131","https://openalex.org/W2121167884","https://openalex.org/W2130851608","https://openalex.org/W2134967412","https://openalex.org/W2151790155","https://openalex.org/W2152311353","https://openalex.org/W2157963336","https://openalex.org/W2158997610","https://openalex.org/W2166047860","https://openalex.org/W2181912024","https://openalex.org/W2210387432","https://openalex.org/W2293952481","https://openalex.org/W2315432931","https://openalex.org/W2406594196","https://openalex.org/W2442924240","https://openalex.org/W2465750682","https://openalex.org/W2625924629","https://openalex.org/W2741029840","https://openalex.org/W2770602608","https://openalex.org/W2952668426","https://openalex.org/W2964049346","https://openalex.org/W3046858608","https://openalex.org/W3091359788","https://openalex.org/W3145974016","https://openalex.org/W4211036025","https://openalex.org/W4235264713","https://openalex.org/W4285022034","https://openalex.org/W4390723842","https://openalex.org/W4399521649","https://openalex.org/W4399548750","https://openalex.org/W6601528862","https://openalex.org/W6606141769","https://openalex.org/W6629171565","https://openalex.org/W6676837791","https://openalex.org/W6677966481","https://openalex.org/W6685975370","https://openalex.org/W6718577050"],"related_works":["https://openalex.org/W2471845753","https://openalex.org/W2389119968","https://openalex.org/W2749535755","https://openalex.org/W2349354219","https://openalex.org/W2475935882","https://openalex.org/W2181341562","https://openalex.org/W2168979046","https://openalex.org/W2992730501","https://openalex.org/W1597797979","https://openalex.org/W2749765834"],"abstract_inverted_index":{"The":[0,110,133,156,239],"term":[1],"<italic":[2],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Text":[4],"Mining</i>":[5],",":[6],"which":[7,149,185],"is":[8,79,115,211,235,248],"given":[9],"to":[10,30,34,98,116,164,183,193,250,256],"the":[11,17,23,48,104,168,212,222,225,232,246,277,296],"set":[12],"of":[13,22,50,91,112,122,158,224],"techniques":[14,127],"used":[15,39,100,166],"for":[16,93,124,148,189,215,299],"extraction,":[18],"cleaning":[19],"and":[20,37,42,65,76,96,119,145,177,192,206,218,273,304],"processing":[21],"information":[24,33],"in":[25,63,101,130,204,221,267,270,290],"texts,":[26,176],"has":[27,58,86],"become":[28,59],"useful":[29,51],"provide":[31],"valuable":[32],"other":[35,240],"algorithms":[36],"widely":[38],"with":[40,128],"statistical":[41,94],"machine":[43],"learning":[44],"methods.":[45],"By":[46],"enabling":[47],"extraction":[49],"insights":[52],"from":[53],"textual":[54],"data,":[55],"Text":[56,197],"Mining":[57],"a":[60,80,236,251],"potent":[61],"tool":[62],"decision-making":[64],"knowledge":[66,107],"discovery":[67],"across":[68],"many":[69],"areas,":[70],"including":[71],"health":[72],"care,":[73],"government,":[74],"education":[75],"industry.":[77],"R":[78,129,181],"mature":[81],"open-source":[82],"programming":[83],"environment":[84],"that":[85,264],"overstepped":[87],"its":[88],"initial":[89],"scope":[90],"application":[92],"computing":[95],"graphics":[97],"be":[99,165],"pretty":[102],"all":[103],"Data":[105],"Science":[106],"Area":[108],"Groups.":[109],"objective":[111],"this":[113,159],"paper":[114,134],"present":[117],"review":[118],"benchmarking":[120],"analysis":[121,298],"packages":[123,138,186,241,263],"text":[125],"mining":[126,198],"computational":[131],"systems.":[132],"reviews":[135],"thirteen":[136],"different":[137],"comparing":[139],"them":[140],"on":[141,244],"their":[142,195],"execution":[143],"time":[144],"memory":[146,271],"used,":[147],"new":[150],"tests":[151],"have":[152,161],"been":[153,162],"specifically":[154],"designed.":[155],"results":[157,288],"approach":[160],"intended":[163],"over":[167],"most":[169],"common":[170],"tasks":[171],"carried":[172],"out":[173,202],"when":[174],"analyzing":[175],"comparisons":[178],"included":[179],"allow":[180],"users":[182],"know":[184],"are":[187,262],"best":[188,213],"each":[190],"task":[191],"improve":[194],"performance.":[196],"package":[199,234],"(tm)":[200],"stands":[201],"particularly":[203],"Tokenization":[205],"Stemming":[207],"techniques,":[208],"while":[209],"fastTextR":[210],"choice":[214,278],"Topic":[216],"Modeling":[217],"Normalization.":[219],"Also":[220],"case":[223],"Term":[226],"Frequency\u2013Inverse":[227],"Document":[228],"Frequency":[229],"(TF-IDF)":[230],"technique,":[231],"textir":[233],"clear":[237],"choice.":[238],"will":[242,294],"depend":[243],"whether":[245],"technique":[247],"applied":[249],"document-term":[252],"matrix":[253],"(DTM)":[254],"or":[255],"plain":[257],"text.":[258],"In":[259],"addition,":[260],"there":[261],"perform":[265],"better":[266,287],"runtime":[268],"than":[269],"usage":[272],"vice":[274],"versa,":[275],"making":[276],"more":[279],"difficult.":[280],"Packages":[281],"such":[282],"as":[283],"udpipe":[284],"can":[285],"achieve":[286],"working":[289],"parallel.":[291],"Future":[292],"works":[293],"include":[295],"same":[297],"parallel":[300],"computing,":[301],"hybrid":[302],"approaches,":[303],"novel":[305],"algorithms.":[306]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}