{"id":"https://openalex.org/W1900124848","doi":"https://doi.org/10.3233/ida-150768","title":"A text mining system for deviation detection in financial documents","display_name":"A text mining system for deviation detection in financial documents","publication_year":2015,"publication_date":"2015-10-09","ids":{"openalex":"https://openalex.org/W1900124848","doi":"https://doi.org/10.3233/ida-150768","mag":"1900124848"},"language":"en","primary_location":{"id":"doi:10.3233/ida-150768","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-150768","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-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/A5088005888","display_name":"Siti Sakira Kamaruddin","orcid":"https://orcid.org/0000-0002-5937-7801"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Siti Sakira Kamaruddin","raw_affiliation_strings":["School of Computing, College of Arts and Sciences, Universiti Utara Malaysia, UUM Sintok, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, College of Arts and Sciences, Universiti Utara Malaysia, UUM Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042883130","display_name":"Azuraliza Abu Bakar","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Azuraliza Abu Bakar","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114202146","display_name":"Abdul Razak Hamdan","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Abdul Razak Hamdan","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033042029","display_name":"Fauzias Mat Nor","orcid":"https://orcid.org/0000-0002-5764-8321"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Fauzias Mat Nor","raw_affiliation_strings":["Graduate School of Business, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","Fax: +60 603 8921 6184","E-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Business, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]},{"raw_affiliation_string":"Fax: +60 603 8921 6184","institution_ids":[]},{"raw_affiliation_string":"E-mail:","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103036102","display_name":"Mohd Zakree Ahmad Nazri","orcid":"https://orcid.org/0000-0003-2267-4965"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohd Zakree Ahmad Nazri","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074274712","display_name":"Zulaiha Ali Othman","orcid":"https://orcid.org/0000-0002-4238-5266"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Zulaiha Ali Othman","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075576405","display_name":"Ghassan Saleh Hussein","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ghassan Saleh Hussein","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042883130"],"corresponding_institution_ids":["https://openalex.org/I885383172"],"apc_list":null,"apc_paid":null,"fwci":2.108,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90402776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"19","issue":"s1","first_page":"S19","last_page":"S44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9908999800682068,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9894000291824341,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8506148457527161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7550178170204163},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6486734747886658},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5516133308410645},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.5449399948120117},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4988417625427246},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46240881085395813},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.435090571641922},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4132218360900879},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36504191160202026},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36242759227752686},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.20085692405700684}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8506148457527161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550178170204163},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6486734747886658},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5516133308410645},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.5449399948120117},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4988417625427246},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46240881085395813},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.435090571641922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4132218360900879},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36504191160202026},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36242759227752686},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.20085692405700684},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/ida-150768","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-150768","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-article"},{"id":"pmh:oai:repo.uum.edu.my:16453","is_oa":false,"landing_page_url":"http://repo.uum.edu.my/16453/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400886","display_name":"Universiti Utara Malaysia Institutional Repository (Universiti Utara Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65079550","host_organization_name":"Universiti Malaysia Perlis","host_organization_lineage":["https://openalex.org/I65079550"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W79683132","https://openalex.org/W194170651","https://openalex.org/W378108201","https://openalex.org/W1532197739","https://openalex.org/W1535737509","https://openalex.org/W1569183990","https://openalex.org/W1571056922","https://openalex.org/W1593305440","https://openalex.org/W1598608964","https://openalex.org/W1636890143","https://openalex.org/W1956559956","https://openalex.org/W1969180667","https://openalex.org/W1970912985","https://openalex.org/W1974287593","https://openalex.org/W1978799756","https://openalex.org/W1980941942","https://openalex.org/W1982743214","https://openalex.org/W2003937960","https://openalex.org/W2005746827","https://openalex.org/W2009964766","https://openalex.org/W2022055320","https://openalex.org/W2027093309","https://openalex.org/W2030836983","https://openalex.org/W2034006258","https://openalex.org/W2035725794","https://openalex.org/W2039958785","https://openalex.org/W2044280671","https://openalex.org/W2072284402","https://openalex.org/W2079978931","https://openalex.org/W2081580037","https://openalex.org/W2081798681","https://openalex.org/W2082056382","https://openalex.org/W2085573882","https://openalex.org/W2110642088","https://openalex.org/W2118067958","https://openalex.org/W2136156070","https://openalex.org/W2140636749","https://openalex.org/W2141148673","https://openalex.org/W2147979708","https://openalex.org/W2151291049","https://openalex.org/W2152096964","https://openalex.org/W2153686960","https://openalex.org/W2154322090","https://openalex.org/W2156986752","https://openalex.org/W2164896167","https://openalex.org/W2169516665","https://openalex.org/W2534669201","https://openalex.org/W3089319657"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W2360644719","https://openalex.org/W2385471969","https://openalex.org/W1522896066"],"abstract_inverted_index":{"Attempts":[0],"to":[1,5,16,49,60,74,95,111,143,162],"mine":[2],"text":[3,40,89],"documents":[4],"discover":[6],"deviations":[7,98,153],"or":[8,54],"anomalies":[9],"have":[10],"increased":[11],"in":[12,23,30,51,80,148,160],"recent":[13],"years":[14],"due":[15],"the":[17,81,120,138,149,158],"elevated":[18],"amount":[19],"of":[20,102,129],"textual":[21,72],"data":[22,25,52],"today's":[24],"repositories.":[26],"Text":[27],"mining":[28,41,90],"assists":[29],"uncovering":[31],"hidden":[32],"information":[33],"contents":[34],"across":[35],"multiple":[36],"documents.":[37,82,104,150],"Although":[38],"various":[39],"tools":[42],"are":[43],"available,":[44],"their":[45,164],"focus":[46],"is":[47,93,141],"mainly":[48],"assist":[50],"summarization":[53],"document":[55],"classification.":[56],"These":[57],"tasks":[58],"proved":[59],"be":[61,155],"helpful,":[62],"however;":[63],"they":[64],"do":[65],"not":[66],"provide":[67,134],"semantic":[68],"analysis":[69],"and":[70],"rigorous":[71],"comparison":[73],"detect":[75,96],"abnormal":[76],"sentences":[77,113,146],"that":[78,92,137],"exist":[79],"In":[83],"this":[84],"paper,":[85],"we":[86],"describe":[87],"a":[88,100,108,130],"system":[91,106,122,140],"able":[94,142],"sentence":[97],"from":[99],"collection":[101],"financial":[103,127],"The":[105,132,151],"implements":[107],"dissimilarity":[109],"function":[110],"compare":[112],"represented":[114],"as":[115],"graphs.":[116],"Our":[117],"evaluation":[118],"on":[119],"proposed":[121,139],"revolves":[123],"around":[124],"experiments":[125],"using":[126],"statements":[128],"bank.":[131],"findings":[133],"valid":[135],"evidence":[136],"identify":[144],"deviating":[145],"occurring":[147],"detected":[152],"can":[154],"beneficial":[156],"for":[157],"authorities":[159],"order":[161],"improve":[163],"business":[165],"decisions.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}
