{"id":"https://openalex.org/W2045285171","doi":"https://doi.org/10.1002/meet.14504901118","title":"Least information document representation for automated text classification","display_name":"Least information document representation for automated text classification","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2045285171","doi":"https://doi.org/10.1002/meet.14504901118","mag":"2045285171"},"language":"en","primary_location":{"id":"doi:10.1002/meet.14504901118","is_oa":false,"landing_page_url":"https://doi.org/10.1002/meet.14504901118","pdf_url":null,"source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","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/A5101031461","display_name":"Weimao Ke","orcid":"https://orcid.org/0000-0002-9961-5827"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weimao Ke","raw_affiliation_strings":["Laboratory for Information, Network & Computing Studies, College of Information Science and Technology, Drexel University, 3141 Chestnut St, Philadelphia, PA 19104"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information, Network & Computing Studies, College of Information Science and Technology, Drexel University, 3141 Chestnut St, Philadelphia, PA 19104","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101031461"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71665896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"49","issue":"1","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9965000152587891,"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/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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/document-classification","display_name":"Document classification","score":0.6923046112060547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6390290856361389},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6273960471153259},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5699304938316345},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5228027105331421},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5129849314689636},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4896707832813263},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4725468158721924},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4680934250354767},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4591201841831207},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4431546628475189},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.413075715303421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36033934354782104},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08663433790206909},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0809197723865509}],"concepts":[{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.6923046112060547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6390290856361389},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6273960471153259},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5699304938316345},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5228027105331421},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5129849314689636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4896707832813263},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4725468158721924},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4680934250354767},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4591201841831207},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4431546628475189},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.413075715303421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36033934354782104},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08663433790206909},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0809197723865509},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/meet.14504901118","is_oa":false,"landing_page_url":"https://doi.org/10.1002/meet.14504901118","pdf_url":null,"source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W641436094","https://openalex.org/W1493526108","https://openalex.org/W1570448133","https://openalex.org/W1965555277","https://openalex.org/W1993657037","https://openalex.org/W1995875735","https://openalex.org/W2024049091","https://openalex.org/W2024932032","https://openalex.org/W2034274945","https://openalex.org/W2077238866","https://openalex.org/W2116237179","https://openalex.org/W2118020653","https://openalex.org/W2119275925","https://openalex.org/W2131604898","https://openalex.org/W2144211451","https://openalex.org/W2147169507","https://openalex.org/W2150102617","https://openalex.org/W2151688820","https://openalex.org/W2163051611","https://openalex.org/W2167044614","https://openalex.org/W2435251607","https://openalex.org/W3090556797","https://openalex.org/W4213009331","https://openalex.org/W4244238212","https://openalex.org/W4252076394","https://openalex.org/W6601052559"],"related_works":["https://openalex.org/W4281569536","https://openalex.org/W2171473894","https://openalex.org/W2611282738","https://openalex.org/W2741230576","https://openalex.org/W2372355498","https://openalex.org/W1561627904","https://openalex.org/W3006526473","https://openalex.org/W2585523118","https://openalex.org/W1573371033","https://openalex.org/W4232107035"],"abstract_inverted_index":{"Abstract":[0],"We":[1,57,134],"propose":[2],"the":[3,55,64,78,97,105,115,144,155,175],"Least":[4],"Information":[5],"theory":[6],"(LIT)":[7],"to":[8,30,44,77,128,151,173],"quantify":[9],"meaning":[10],"of":[11,80,99,177,187],"information":[12,36,75,95,191],"in":[13,51,54,63,85,114,142,166],"probability":[14,49],"distributions":[15,50,113],"and":[16,37,88,121,162,182],"derive":[17],"a":[18,32,81,86,100,184],"new":[19,185],"document":[20,65,116],"representation":[21],"model":[22],"for":[23,96,131,189],"text":[24,132],"classification.":[25,133,194],"By":[26],"extending":[27],"Shannon":[28],"entropy":[29],"accommodate":[31],"non\u2010linear":[33],"relation":[34],"between":[35],"uncertainty,":[38],"LIT":[39],"offers":[40,183],"an":[41],"information\u2010centric":[42],"approach":[43],"weight":[45,61],"terms":[46],"based":[47],"on":[48,138],"documents":[52,130],"vs.":[53],"collection.":[56],"develop":[58],"two":[59],"term":[60,103,112],"quantities":[62,108],"classification":[66,136],"context:":[67],"1)":[68],"LI":[69,90],"Binary":[70],"(LIB)":[71],"which":[72,93,143,159],"quantifies":[73],"(least)":[74],"due":[76],"observation":[79,98],"term's":[82],"(binary)":[83],"occurrence":[84],"document;":[87],"2)":[89],"Frequency":[91],"(LIF)":[92],"measures":[94],"randomly":[101],"picked":[102],"from":[104],"document.":[106],"Both":[107],"are":[109],"computed":[110],"given":[111],"collection":[117],"as":[118],"prior":[119],"knowledge":[120],"can":[122],"be":[123],"used":[124],"separately":[125],"or":[126],"combined":[127],"represent":[129],"conduct":[135],"experiments":[137],"three":[139],"benchmark":[140],"collections,":[141],"proposed":[145],"methods":[146],"show":[147],"strong":[148],"performances":[149],"compared":[150],"classic":[152],"TF*IDF.":[153],"Particularly,":[154],"LIB*LIF":[156,178],"weighting":[157],"scheme,":[158],"combines":[160],"LIB":[161],"LIF,":[163],"outperforms":[164],"TF*IDF":[165],"several":[167],"experimental":[168],"settings.":[169],"Despite":[170],"its":[171],"similarity":[172],"TF*IDF,":[174],"formulation":[176],"is":[179],"very":[180],"different":[181],"way":[186],"thinking":[188],"modeling":[190],"processes":[192],"beyond":[193]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}