{"id":"https://openalex.org/W2136175947","doi":"https://doi.org/10.1214/07-ss016","title":"Text Data Mining: Theory and Methods","display_name":"Text Data Mining: Theory and Methods","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2136175947","doi":"https://doi.org/10.1214/07-ss016","mag":"2136175947"},"language":"en","primary_location":{"id":"doi:10.1214/07-ss016","doi":"https://doi.org/10.1214/07-ss016","is_oa":true,"landing_page_url":"https://doi.org/10.1214/07-ss016","pdf_url":"https://projecteuclid.org/journals/statistics-surveys/volume-2/issue-none/Text-Data-Mining-Theory-and-Methods/10.1214/07-SS016.pdf","source":{"id":"https://openalex.org/S147498506","display_name":"Statistics Surveys","issn_l":"1935-7516","issn":["1935-7516"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","jufo-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315749","host_organization_name":"American Statistical Association","host_organization_lineage":["https://openalex.org/P4310315749"],"host_organization_lineage_names":["American Statistical Association"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics Surveys","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://projecteuclid.org/journals/statistics-surveys/volume-2/issue-none/Text-Data-Mining-Theory-and-Methods/10.1214/07-SS016.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jeffrey L. Solka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4388482641","display_name":"NSWC Dahlgren Division","ror":"https://ror.org/04yrq0159","country_code":"US","type":"facility","lineage":["https://openalex.org/I1328969757","https://openalex.org/I1330347796","https://openalex.org/I2802287952","https://openalex.org/I3130687028","https://openalex.org/I4388482641"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey L. Solka","raw_affiliation_strings":["Naval Surface Warfare Center Dahlgren Division Attention Jeff Solka 18444 Frontage Rd , Suite 328 Dahlgren Virginia , 22448-5161"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval Surface Warfare Center Dahlgren Division Attention Jeff Solka 18444 Frontage Rd , Suite 328 Dahlgren Virginia , 22448-5161","institution_ids":["https://openalex.org/I4388482641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4388482641"],"apc_list":null,"apc_paid":null,"fwci":17.3931,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.98934159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"none","first_page":"94","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9384999871253967,"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":0.9384999871253967,"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":0.025599999353289604,"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":0.0142000000923872,"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":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204999923706055},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2312999963760376},{"id":"https://openalex.org/C194541083","wikidata":"https://www.wikidata.org/wiki/Q457174","display_name":"Workaround","level":2,"score":0.22859999537467957},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22750000655651093},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.22509999573230743},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.22370000183582306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.22349999845027924},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2190999984741211}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1214/07-ss016","doi":"https://doi.org/10.1214/07-ss016","is_oa":true,"landing_page_url":"https://doi.org/10.1214/07-ss016","pdf_url":"https://projecteuclid.org/journals/statistics-surveys/volume-2/issue-none/Text-Data-Mining-Theory-and-Methods/10.1214/07-SS016.pdf","source":{"id":"https://openalex.org/S147498506","display_name":"Statistics Surveys","issn_l":"1935-7516","issn":["1935-7516"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","jufo-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315749","host_organization_name":"American Statistical Association","host_organization_lineage":["https://openalex.org/P4310315749"],"host_organization_lineage_names":["American Statistical Association"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:0807.2569","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0807.2569","pdf_url":"https://arxiv.org/pdf/0807.2569","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CULeuclid:euclid.ssu/1216238228","doi":null,"is_oa":false,"landing_page_url":"http://projecteuclid.org/euclid.ssu/1216238228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400787","display_name":"Project Euclid (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.48550/arxiv.0807.2569","doi":"https://doi.org/10.48550/arxiv.0807.2569","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.0807.2569","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1214/07-ss016","doi":"https://doi.org/10.1214/07-ss016","is_oa":true,"landing_page_url":"https://doi.org/10.1214/07-ss016","pdf_url":"https://projecteuclid.org/journals/statistics-surveys/volume-2/issue-none/Text-Data-Mining-Theory-and-Methods/10.1214/07-SS016.pdf","source":{"id":"https://openalex.org/S147498506","display_name":"Statistics Surveys","issn_l":"1935-7516","issn":["1935-7516"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","jufo-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315749","host_organization_name":"American Statistical Association","host_organization_lineage":["https://openalex.org/P4310315749"],"host_organization_lineage_names":["American Statistical Association"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136175947.pdf","grobid_xml":"https://content.openalex.org/works/W2136175947.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W70934230","https://openalex.org/W166013858","https://openalex.org/W286208473","https://openalex.org/W340455601","https://openalex.org/W1480230335","https://openalex.org/W1486589216","https://openalex.org/W1505935962","https://openalex.org/W1507045023","https://openalex.org/W1515705254","https://openalex.org/W1528120972","https://openalex.org/W1535854520","https://openalex.org/W1555585125","https://openalex.org/W1597985255","https://openalex.org/W1606161385","https://openalex.org/W1651093245","https://openalex.org/W1742512077","https://openalex.org/W1971318281","https://openalex.org/W1981081578","https://openalex.org/W1984096507","https://openalex.org/W2001141328","https://openalex.org/W2013387118","https://openalex.org/W2027077102","https://openalex.org/W2038813691","https://openalex.org/W2045108252","https://openalex.org/W2049607461","https://openalex.org/W2053186076","https://openalex.org/W2064568176","https://openalex.org/W2086876270","https://openalex.org/W2097308346","https://openalex.org/W2098162425","https://openalex.org/W2100484636","https://openalex.org/W2107425660","https://openalex.org/W2113359929","https://openalex.org/W2118020653","https://openalex.org/W2119955173","https://openalex.org/W2127284416","https://openalex.org/W2133576408","https://openalex.org/W2134866961","https://openalex.org/W2136668284","https://openalex.org/W2146154212","https://openalex.org/W2146820706","https://openalex.org/W2147152072","https://openalex.org/W2479500547","https://openalex.org/W2481759777","https://openalex.org/W2543374392","https://openalex.org/W4250363620","https://openalex.org/W4292023222"],"related_works":["https://openalex.org/W7216925582","https://openalex.org/W4205505447","https://openalex.org/W2472055364","https://openalex.org/W6944194508","https://openalex.org/W2809684381","https://openalex.org/W2567329814","https://openalex.org/W2602957669","https://openalex.org/W331312376","https://openalex.org/W1904543801","https://openalex.org/W2365299969"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"the":[3,13,29,34,46,50,56,65,68,83],"reader":[4,30,51,84],"with":[5,85],"a":[6,72,86],"very":[7,73],"brief":[8],"introduction":[9],"to":[10,27,31,61],"some":[11,32,54,77],"of":[12,17,23,33,53,55,78,88],"theory":[14],"and":[15],"methods":[16],"text":[18],"data":[19],"mining.":[20],"The":[21],"intent":[22],"this":[24,41],"article":[25],"is":[26],"introduce":[28],"current":[35],"methodologies":[36],"that":[37,59],"are":[38],"employed":[39],"within":[40,64],"discipline":[42],"area":[43],"while":[44,80],"at":[45],"same":[47],"time":[48],"making":[49],"aware":[52],"interesting":[57],"challenges":[58],"remain":[60],"be":[62],"solved":[63],"area.":[66],"Finally,":[67],"articles":[69],"serves":[70],"as":[71],"rudimentary":[74],"tutorial":[75],"on":[76],"techniques":[79],"also":[81],"providing":[82],"list":[87],"references":[89],"for":[90],"additional":[91],"study.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2016-06-24T00:00:00"}