{"id":"https://openalex.org/W2005088791","doi":"https://doi.org/10.1145/1099554.1099655","title":"A structure-sensitive framework for text categorization","display_name":"A structure-sensitive framework for text categorization","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2005088791","doi":"https://doi.org/10.1145/1099554.1099655","mag":"2005088791"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089606464","display_name":"Ganesh Ramakrishnan","orcid":"https://orcid.org/0000-0003-4533-2490"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh Ramakrishnan","raw_affiliation_strings":["IBM IRL, New Delhi, India","IBM, IRL, New Delhi, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM IRL, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, IRL, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109880182","display_name":"Deepa Paranjpe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepa Paranjpe","raw_affiliation_strings":["Shankar Nagar, Nagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shankar Nagar, Nagpur, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17217147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8047881126403809},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7874891757965088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7194856405258179},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6748813390731812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6608058214187622},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5947406888008118},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5589237809181213},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5108818411827087},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5000913143157959},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.4556262493133545},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43502679467201233},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3892626464366913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10394081473350525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047881126403809},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7874891757965088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7194856405258179},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6748813390731812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6608058214187622},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5947406888008118},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5589237809181213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5108818411827087},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5000913143157959},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.4556262493133545},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43502679467201233},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3892626464366913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10394081473350525},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1099554.1099655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W206499635","https://openalex.org/W1527532815","https://openalex.org/W1578881253","https://openalex.org/W1941537533","https://openalex.org/W2002393437","https://openalex.org/W2045577803","https://openalex.org/W2066619786","https://openalex.org/W2070589943","https://openalex.org/W2097606805","https://openalex.org/W2107425660","https://openalex.org/W2116129845","https://openalex.org/W2123504579","https://openalex.org/W2143517590","https://openalex.org/W2167072947"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"This":[0,211],"paper":[1],"presents":[2],"a":[3,46,90,145],"framework":[4],"called":[5,120],"Structure":[6],"Sensitive":[7],"CATegorization(SSCAT),":[8],"that":[9,31,92,99,147,224],"exploits":[10,93],"document":[11],"structure":[12,231],"for":[13,84,170],"improved":[14],"categorization.":[15,238],"There":[16],"are":[17,64,100,125,165],"two":[18],"parts":[19],"to":[20],"this":[21],"framework,":[22],"viz.":[23],"(1)":[24],"Documents":[25],"often":[26],"have":[27],"layout":[28],"structure,":[29],"such":[30,103,235],"logically":[32],"coherent":[33],"text":[34,237],"is":[35,141],"grouped":[36],"together":[37],"into":[38],"fields":[39,98,161,173],"using":[40],"some":[41],"mark-up":[42],"language.":[43],"We":[44,88],"use":[45],"log-linear":[47],"model,":[48],"which":[49],"associates":[50,107],"one":[51,188],"or":[52],"more":[53],"features":[54,63,79,150,169,226],"with":[55,60,109,134,162],"each":[56],"field.":[57],"Weights":[58],"associated":[59],"the":[61,73,77,82,85,94,135,153,171,175,182,215],"field":[62,78],"learnt":[65,126],"from":[66,127,152,191],"training":[67,144],"data":[68],"and":[69,106,207],"these":[70,112],"weights":[71,108,116,124],"quantify":[72],"per-class":[74],"importance":[75],"of":[76,97,117,130,186,199,217],"in":[80,111,160,167,174],"determining":[81],"category":[83],"document.":[86],"(2)":[87],"employ":[89],"technique":[91],"parse":[95,155],"tree":[96],"phrasal":[101,131,163],"constructs,":[102,132,164],"as":[104,236],"title":[105],"words":[110,119],"constructs":[113],"while":[114],"boosting":[115],"important":[118],"focus":[121,137],"words.":[122,138],"These":[123],"example":[128],"instances":[129],"marked":[133],"corresponding":[136,172],"The":[139,157],"learning":[140],"accomplished":[142],"by":[143],"classifier":[146,203],"uses":[148],"linguistic":[149,225],"obtained":[151],"text's":[154],"structure.":[156],"weighted":[158],"words,":[159],"used":[166],"obtaining":[168],"overall":[176],"framework.":[177],"SSCAT":[178,218],"was":[179],"tested":[180],"on":[181,228],"supervised":[183],"categorization":[184],"task":[185],"over":[187,200],"million":[189],"products":[190],"Yahoo!'s":[192],"on-line":[193],"shopping":[194],"data.":[195],"With":[196],"an":[197],"accuracy":[198],"90%,":[201],"our":[202,222],"outperforms":[204],"Naive":[205],"Bayes":[206],"Support":[208],"Vector":[209],"Machines.":[210],"not":[212],"only":[213],"shows":[214],"effectiveness":[216],"but":[219],"also":[220],"strengthens":[221],"belief":[223],"based":[227],"natural":[229],"language":[230],"can":[232],"improve":[233],"tasks":[234]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}