{"id":"https://openalex.org/W4292605239","doi":"https://doi.org/10.1093/obo/9780199772810-0295","title":"Text Mining","display_name":"Text Mining","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4292605239","doi":"https://doi.org/10.1093/obo/9780199772810-0295"},"language":"en","primary_location":{"id":"doi:10.1093/obo/9780199772810-0295","doi":"https://doi.org/10.1093/obo/9780199772810-0295","is_oa":false,"landing_page_url":"https://doi.org/10.1093/obo/9780199772810-0295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Oxford Bibliographies in Linguistics","raw_type":"reference-entry"},"volume":{"id":"https://openalex.org/W7166580408","display_name":"Oxford Bibliographies in Linguistics"},"type":"reference-entry","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":null,"display_name":"Carlos Peri\u00f1\u00e1n-Pascual","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos Peri\u00f1\u00e1n-Pascual","raw_affiliation_strings":["Profesor, Dpto. de Ling\u00fc\u00edstica Aplicada, Universitat Polit\u00e8cnica de Val\u00e8ncia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Profesor, Dpto. de Ling\u00fc\u00edstica Aplicada, Universitat Polit\u00e8cnica de Val\u00e8ncia","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.40310001373291016,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.40310001373291016,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.23680000007152557,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.23160000145435333,"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/text-mining","display_name":"text mining","score":0.9980000257492065},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.6169999837875366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.8230000138282776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.8289999961853027},{"id":"https://openalex.org/keywords/web-mining","display_name":"web mining","score":0.7789999842643738},{"id":"https://openalex.org/keywords/information-overload","display_name":"information overload","score":0.8410000205039978},{"id":"https://openalex.org/keywords/social-media-content","display_name":"social media content","score":0.5600000023841858},{"id":"https://openalex.org/keywords/data-fusion","display_name":"data fusion","score":0.8009999990463257},{"id":"https://openalex.org/keywords/knowledge-discovery","display_name":"knowledge discovery","score":0.5249999761581421},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.8730000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367371916770935},{"id":"https://openalex.org/C176775163","wikidata":"https://www.wikidata.org/wiki/Q5158396","display_name":"Concept mining","level":4,"score":0.7257530689239502},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.6885510683059692},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.6446448564529419},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6087741851806641},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.498457670211792},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.49649864435195923},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48610615730285645},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4846275746822357},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.47394517064094543},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4722698926925659},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4553861618041992},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.43746042251586914},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.43407002091407776},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.43017470836639404},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42845430970191956},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41787129640579224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3774499297142029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35797205567359924},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.33595776557922363},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3165576457977295},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23488962650299072},{"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:10.1093/obo/9780199772810-0295","doi":"https://doi.org/10.1093/obo/9780199772810-0295","is_oa":false,"landing_page_url":"https://doi.org/10.1093/obo/9780199772810-0295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Oxford Bibliographies in Linguistics","raw_type":"reference-entry"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W143239782","https://openalex.org/W782030620","https://openalex.org/W1128809682","https://openalex.org/W1826790618","https://openalex.org/W1964613733","https://openalex.org/W1972640883","https://openalex.org/W1984762104","https://openalex.org/W2004450254","https://openalex.org/W2007407316","https://openalex.org/W2020278455","https://openalex.org/W2028962062","https://openalex.org/W2045181608","https://openalex.org/W2082554333","https://openalex.org/W2094515246","https://openalex.org/W2112422413","https://openalex.org/W2118020653","https://openalex.org/W2122522916","https://openalex.org/W2149684865","https://openalex.org/W2166706824","https://openalex.org/W2215376118","https://openalex.org/W2218641061","https://openalex.org/W2234490075","https://openalex.org/W2250539671","https://openalex.org/W2251803266","https://openalex.org/W2295223795","https://openalex.org/W2296283641","https://openalex.org/W2317879529","https://openalex.org/W2405765071","https://openalex.org/W2415973339","https://openalex.org/W2485709337","https://openalex.org/W2493566995","https://openalex.org/W2493916176","https://openalex.org/W2605369679","https://openalex.org/W2773770599","https://openalex.org/W2779594574","https://openalex.org/W2785105945","https://openalex.org/W2787560479","https://openalex.org/W2809975818","https://openalex.org/W2901387348","https://openalex.org/W2937423263","https://openalex.org/W2956158857","https://openalex.org/W2956530858","https://openalex.org/W2957007523","https://openalex.org/W2965647350","https://openalex.org/W2968280451","https://openalex.org/W2970650542","https://openalex.org/W3037458976","https://openalex.org/W3043222912","https://openalex.org/W3088164486","https://openalex.org/W3129055730","https://openalex.org/W3131198033","https://openalex.org/W3164029002","https://openalex.org/W3167441071","https://openalex.org/W3179747003","https://openalex.org/W3191804854","https://openalex.org/W3195990001","https://openalex.org/W4230209322","https://openalex.org/W4231824253","https://openalex.org/W4233906183","https://openalex.org/W4234270840","https://openalex.org/W4238049007","https://openalex.org/W4240409582","https://openalex.org/W4244166797","https://openalex.org/W4245888765","https://openalex.org/W4246492507"],"related_works":["https://openalex.org/W2375663702","https://openalex.org/W80463681","https://openalex.org/W2384103846","https://openalex.org/W2168979046","https://openalex.org/W2602957669","https://openalex.org/W7100792019","https://openalex.org/W7095208141","https://openalex.org/W2567064004","https://openalex.org/W2181341562","https://openalex.org/W4290662500"],"abstract_inverted_index":{"Text":[0,55],"data":[1,60,66,80,86,100,144,153,188,211],"mining,":[2,6,61,177],"or":[3,98],"simply":[4],"text":[5,16,44,53,92,106,114,124,127,141,158,206],"encompasses":[7],"tasks":[8,241],"that":[9,242],"typically":[10],"analyze":[11,183],"vast":[12],"amounts":[13],"of":[14,20,37,49,65,75,105,152,166,172,196],"digitized":[15],"to":[17,95,168,180,229],"detect":[18],"patterns":[19],"use":[21,74],"and":[22,119,182,225,235],"then":[23],"extract":[24,244],"useful":[25],"information":[26,173,185,245],"in":[27,72,102,113,133,154,193,205],"the":[28,47,73,103,131,149,155,170,190,194],"search":[29],"for":[30,146],"knowledge;":[31],"thus,":[32],"it":[33],"is":[34,46,57,216],"one":[35],"way":[36],"achieving":[38],"artificial":[39],"intelligence.":[40],"In":[41],"other":[42],"words,":[43],"mining":[45,56,81,93,115,128,159,207],"process":[48,96],"extracting":[50,120],"value":[51],"from":[52,123,130,186,199,232,246],"data.":[54,125],"grounded":[58],"on":[59,117,189],"so":[62],"both":[63],"fields":[64],"science":[67],"share":[68],"many":[69],"similarities,":[70],"e.g.,":[71],"machine":[76,222],"learning":[77,223],"algorithms.":[78],"However,":[79],"usually":[82],"deals":[83],"with":[84],"structured":[85,143],"sets":[87],"containing":[88],"numerical":[89],"data,":[90,234],"whereas":[91],"aims":[94,179],"unstructured":[97,140],"semi-structured":[99],"mainly":[101],"form":[104],"documents.":[107],"For":[108],"this":[109],"reason,":[110],"pre-processing":[111],"techniques":[112],"focus":[116],"identifying":[118],"significant":[121,203],"features":[122],"Moreover,":[126],"benefits":[129],"advances":[132,204],"natural":[134],"language":[135],"processing,":[136],"particularly":[137],"when":[138],"transforming":[139],"into":[142,218],"suitable":[145],"analysis.":[147],"With":[148],"exponential":[150],"growth":[151],"Internet":[156],"era,":[157],"has":[160],"attracted":[161],"much":[162],"attention":[163],"as":[164,192],"part":[165],"efforts":[167],"reduce":[169],"problem":[171],"overload.":[174],"Indeed,":[175],"Web":[176,191],"which":[178,227,238],"discover":[181,230],"relevant":[184],"heterogeneous":[187],"case":[195],"user-generated":[197],"content":[198],"social":[200],"media,":[201],"requires":[202],"technologies":[208],"within":[209],"a":[210],"fusion":[212],"framework.":[213],"This":[214],"article":[215],"organized":[217],"two":[219],"main":[220],"topics:":[221],"models":[224],"algorithms,":[226],"aim":[228],"knowledge":[231],"new":[233],"text-mining":[236],"applications,":[237],"illustrate":[239],"various":[240],"can":[243],"texts.":[247]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2022-08-22T00:00:00"}