{"id":"https://openalex.org/W42456016","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch104","title":"Discovering Unknown Patterns in Free Text","display_name":"Discovering Unknown Patterns in Free Text","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W42456016","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch104","mag":"42456016"},"language":"en","primary_location":{"id":"doi:10.4018/978-1-60566-010-3.ch104","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-60566-010-3.ch104","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Data Warehousing and Mining, Second Edition","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W2587851609","display_name":"Encyclopedia of Data Warehousing and Mining, Second Edition"},"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":"https://openalex.org/A5024461310","display_name":"Jan Hendrik Kroeze","orcid":"https://orcid.org/0000-0001-7118-4853","observed_orcids":["https://orcid.org/0000-0001-7118-4853"]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Jan H Kroeze","raw_affiliation_strings":["University of Pretoria, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pretoria, South Africa","institution_ids":["https://openalex.org/I69552723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024461310"],"corresponding_institution_ids":["https://openalex.org/I69552723"],"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":"669","last_page":"675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.43380001187324524,"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":0.43380001187324524,"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":0.2896000146865845,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.12300000339746475,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":1.0},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.8529999852180481},{"id":"https://openalex.org/keywords/pattern-discovery","display_name":"pattern discovery","score":0.781000018119812},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"unstructured data","score":0.8740000128746033},{"id":"https://openalex.org/keywords/text-mining-applications","display_name":"text mining applications","score":0.7089999914169312},{"id":"https://openalex.org/keywords/data-visualization","display_name":"data visualization","score":0.6200000047683716},{"id":"https://openalex.org/keywords/future-directions","display_name":"future research directions","score":0.7900000214576721}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6488975286483765},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.6167262196540833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5948618054389954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.549175500869751},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4890197217464447},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.486970990896225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4740312397480011},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45160895586013794},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4200672507286072},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31865572929382324},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28046953678131104},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.22173982858657837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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:10.4018/978-1-60566-010-3.ch104","doi":"https://doi.org/10.4018/978-1-60566-010-3.ch104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-60566-010-3.ch104","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Data Warehousing and Mining, Second Edition","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W113111301","https://openalex.org/W580355855","https://openalex.org/W1497391961","https://openalex.org/W1498382685","https://openalex.org/W1860584505","https://openalex.org/W1902383004","https://openalex.org/W1989795039","https://openalex.org/W1994224927","https://openalex.org/W2000461758","https://openalex.org/W2006840868","https://openalex.org/W2008527839","https://openalex.org/W2008735451","https://openalex.org/W2033319677","https://openalex.org/W2035574181","https://openalex.org/W2035716223","https://openalex.org/W2040022066","https://openalex.org/W2040573546","https://openalex.org/W2078862361","https://openalex.org/W2110788923","https://openalex.org/W2121940249","https://openalex.org/W2143079781","https://openalex.org/W2158040974","https://openalex.org/W2254442469","https://openalex.org/W2291731792","https://openalex.org/W6602837053","https://openalex.org/W6680704940"],"related_works":["https://openalex.org/W4405524044","https://openalex.org/W2132453123","https://openalex.org/W2761917259","https://openalex.org/W1538359285","https://openalex.org/W1904718356","https://openalex.org/W2602957669","https://openalex.org/W2396927397","https://openalex.org/W1486198364","https://openalex.org/W4281699919","https://openalex.org/W2735827657"],"abstract_inverted_index":{"A":[0],"very":[1],"large":[2],"percentage":[3],"of":[4,17,71,123,155,196,203],"business":[5],"and":[6,24,49,73,90,108,160,181,194,205],"academic":[7],"data":[8,27,37,43,94,166,170],"is":[9,28,56,104,135,141],"stored":[10],"in":[11,38,51,64,93,115,121],"textual":[12,125],"format.":[13],"With":[14],"the":[15,33,57,69,118,149,153,176,179,191],"exception":[16],"metadata,":[18],"such":[19],"as":[20],"author,":[21],"date,":[22],"title":[23],"publisher,":[25],"this":[26],"not":[29],"overtly":[30],"structured":[31,169],"like":[32],"standard,":[34],"mainly":[35],"numerical,":[36],"relational":[39],"databases.":[40],"Parallel":[41],"to":[42,68,144],"mining,":[44,157],"which":[45,190],"finds":[46],"new":[47],"patterns":[48,63],"trends":[50],"numerical":[52],"data,":[53],"text":[54,156,184,197],"mining":[55,84,103,134,167,185,198],"process":[58],"aimed":[59],"at":[60],"discovering":[61],"unknown":[62,143],"free":[65],"text.":[66],"Owing":[67],"importance":[70,202],"competitive":[72],"scientific":[74],"knowledge":[75],"that":[76,132,140,151],"can":[77],"be":[78,187,211],"exploited":[79],"from":[80],"these":[81],"texts,":[82],"\u201ctext":[83,133],"has":[85],"become":[86],"an":[87,105,136],"increasingly":[88],"popular":[89],"essential":[91],"theme":[92],"mining\u201d":[95],"(Han":[96],"&":[97],"Kamber,":[98],"2001,":[99],"p.":[100,129],"428).":[101],"Text":[102],"evolving":[106],"field":[107],"its":[109],"relatively":[110,142],"short":[111],"history":[112],"goes":[113],"hand":[114,116],"with":[117],"recent":[119],"explosion":[120],"availability":[122],"electronic":[124],"information.":[126],"Chen":[127],"(2001,":[128],"vi)":[130],"remarks":[131],"emerging":[137],"technical":[138],"area":[139],"IT":[145],"professions\u201d.":[146],"This":[147],"explains":[148],"fact":[150],"despite":[152],"value":[154],"most":[158],"research":[159,219],"development":[161],"efforts":[162],"still":[163],"focus":[164],"on":[165],"using":[168],"(Fan":[171],"et":[172],"al.,":[173],"2006).":[174],"In":[175],"next":[177],"section,":[178],"background":[180],"need":[182],"for":[183,217],"will":[186,209],"discussed":[188,212],"after":[189],"various":[192],"uses":[193],"techniques":[195],"are":[199],"described.":[200],"The":[201],"visualisation":[204],"some":[206,215],"critical":[207],"issues":[208],"then":[210],"followed":[213],"by":[214],"suggestions":[216],"future":[218],"topics.":[220]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
