{"id":"https://openalex.org/W1966346498","doi":"https://doi.org/10.1198/004017006000000471","title":"Mining and Tracking Massive Text Data: Classification, Construction of Tracking Statistics, and Inference Under Misclassification","display_name":"Mining and Tracking Massive Text Data: Classification, Construction of Tracking Statistics, and Inference Under Misclassification","publication_year":2007,"publication_date":"2007-04-19","ids":{"openalex":"https://openalex.org/W1966346498","doi":"https://doi.org/10.1198/004017006000000471","mag":"1966346498"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1198/004017006000000471","pdf_url":null,"source":{"id":"https://openalex.org/S985303","display_name":"Technometrics","issn_l":"0040-1706","issn":["0040-1706","1537-2723"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5034400738","display_name":"Daniel R. Jeske","orcid":"https://orcid.org/0000-0002-0214-7992"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R Jeske","raw_affiliation_strings":["University of California, at Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, at Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047848770","display_name":"Regina Y. Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regina Y Liu","raw_affiliation_strings":["School of Arts and Sciences, Statistics"],"affiliations":[{"raw_affiliation_string":"School of Arts and Sciences, Statistics","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.251,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":16,"citation_normalized_percentile":{"value":0.970515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":86,"max":87},"biblio":{"volume":"49","issue":"2","first_page":"116","last_page":"128"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9949,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9949,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9939,"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":0.9929,"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/tracking","display_name":"Tracking (education)","score":0.56818044},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.4144123},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical Inference","score":0.41079068}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.73631763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67982435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6385784},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.56818044},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.4144123},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.41079068},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.373981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3301124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12030691},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1198/004017006000000471","pdf_url":null,"source":{"id":"https://openalex.org/S985303","display_name":"Technometrics","issn_l":"0040-1706","issn":["0040-1706","1537-2723"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1495929194","https://openalex.org/W1505937442","https://openalex.org/W1554944419","https://openalex.org/W1572615921","https://openalex.org/W1604792744","https://openalex.org/W1924689489","https://openalex.org/W1973682096","https://openalex.org/W1983435698","https://openalex.org/W1989747332","https://openalex.org/W2020116222","https://openalex.org/W2026632944","https://openalex.org/W2049642487","https://openalex.org/W2053463056","https://openalex.org/W2067787182","https://openalex.org/W2097089247","https://openalex.org/W2102650424","https://openalex.org/W2118250684","https://openalex.org/W2137591261","https://openalex.org/W2150290224","https://openalex.org/W2166183437","https://openalex.org/W2168022998","https://openalex.org/W2169775947","https://openalex.org/W2320240088","https://openalex.org/W2594825694","https://openalex.org/W3102221121","https://openalex.org/W4229849575","https://openalex.org/W4242831698","https://openalex.org/W4249751075","https://openalex.org/W4252605513","https://openalex.org/W4255085141","https://openalex.org/W4256540010","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4286952477","https://openalex.org/W3000984192","https://openalex.org/W2996812256","https://openalex.org/W2525543468","https://openalex.org/W2389929639","https://openalex.org/W2366743900","https://openalex.org/W2103073163","https://openalex.org/W2026490863","https://openalex.org/W1996877595","https://openalex.org/W137830373"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3],"comprehensive":[4],"data-mining":[5,83],"procedure":[6,32,84],"for":[7,59,69],"exploring":[8],"large":[9],"freestyle":[10],"text":[11,34,49],"datasets":[12],"to":[13,24,87,94],"discover":[14],"useful":[15],"features":[16],"and":[17,44,52,74],"develop":[18],"suitable":[19],"tracking":[20,38,53,70],"statistics":[21,54,71],"(often":[22],"referred":[23],"as":[25,77],"performance":[26],"measures":[27],"or":[28,63,102],"risk":[29,45,100],"indicators).":[30],"The":[31],"includes":[33],"classification,":[35],"construction":[36],"of":[37],"statistics,":[39],"inference":[40,68],"under":[41],"error":[42,64],"measurements,":[43],"analysis.":[46],"Some":[47],"specific":[48],"analysis":[50],"methodologies":[51],"are":[55,72],"discussed.":[56],"Several":[57],"approaches":[58],"incorporating":[60],"misclassified":[61],"data":[62],"measurements":[65],"into":[66],"the":[67,81],"proposed":[73,82],"evaluated.":[75],"Finally,":[76],"an":[78,89],"illustrative":[79],"example,":[80],"is":[85],"applied":[86],"analyzing":[88],"aviation":[90,99],"safety":[91],"report":[92],"repository":[93],"show":[95],"its":[96],"utility":[97],"in":[98],"management":[101],"general":[103],"decision-support":[104],"systems.":[105]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1966346498","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-01-18T19:38:25.105389","created_date":"2016-06-24"}