{"id":"https://openalex.org/W2034151685","doi":"https://doi.org/10.1145/1277741.1277975","title":"Text categorization for streams","display_name":"Text categorization for streams","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2034151685","doi":"https://doi.org/10.1145/1277741.1277975","mag":"2034151685"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-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":null,"display_name":"D. L. Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"D. L. Thomas","raw_affiliation_strings":["University Of Wales: Bangor, Bangor, Wales, UK"],"affiliations":[{"raw_affiliation_string":"University Of Wales: Bangor, Bangor, Wales, UK","institution_ids":["https://openalex.org/I161548249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025875274","display_name":"William J. Teahan","orcid":"https://orcid.org/0000-0003-3640-6750"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"W. J. Teahan","raw_affiliation_strings":["University Of Wales: Bangor, Bangor, Wales, UK"],"affiliations":[{"raw_affiliation_string":"University Of Wales: Bangor, Bangor, Wales, UK","institution_ids":["https://openalex.org/I161548249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161548249"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08851365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"907","last_page":"907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9876000285148621,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9876000285148621,"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":0.9861999750137329,"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":0.9732999801635742,"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/ascription","display_name":"Ascription","score":0.8290420770645142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819992303848267},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7155942320823669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6077374815940857},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5581362247467041},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5384929180145264},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.49991774559020996},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.47036075592041016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4589025378227234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4512830674648285},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.414816677570343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30223581194877625},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2885303497314453},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0615537166595459}],"concepts":[{"id":"https://openalex.org/C2779279129","wikidata":"https://www.wikidata.org/wiki/Q4804076","display_name":"Ascription","level":2,"score":0.8290420770645142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819992303848267},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7155942320823669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6077374815940857},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5581362247467041},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5384929180145264},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.49991774559020996},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.47036075592041016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4589025378227234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4512830674648285},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.414816677570343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30223581194877625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2885303497314453},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0615537166595459},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1277741.1277975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W94150857","https://openalex.org/W1533268326","https://openalex.org/W1974927094","https://openalex.org/W2028455782","https://openalex.org/W2070509841","https://openalex.org/W2161628678"],"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":{"We":[0],"describe":[1],"a":[2,21,75],"novel":[3],"system":[4,41,66],"for":[5],"evaluating":[6],"and":[7,61],"performing":[8],"stream-based":[9],"text":[10,13,17,51],"categorization.":[11],"Stream-based":[12],"categorization":[14],"considers":[15],"the":[16,28,38,49,65],"being":[18],"categorized":[19],"as":[20,55,59,83],"stream":[22],"of":[23,64,70],"symbols,":[24],"which":[25,32],"differs":[26],"from":[27,37],"traditional":[29],"feature-based":[30,76],"approach":[31],"relies":[33],"on":[34,48],"extracting":[35],"features":[36],"text.":[39],"The":[40],"implements":[42],"character-based":[43],"languages":[44],"models--specifically":[45],"models":[46],"based":[47],"PPM":[50],"compression":[52],"scheme--as":[53],"well":[54],"count-based":[56],"measures":[57],"such":[58,82],"R-Measure":[60],"C-Measure.":[62],"Use":[63],"demonstrates":[67],"that":[68],"all":[69],"these":[71],"techniques":[72],"outperform":[73],"SVM,":[74],"classifier,":[77],"at":[78],"stream-related":[79],"classification":[80],"tasks":[81],"authorship":[84],"ascription.":[85]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}