{"id":"https://openalex.org/W2070509841","doi":"https://doi.org/10.1145/1008992.1009129","title":"Context-based methods for text categorisation","display_name":"Context-based methods for text categorisation","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2070509841","doi":"https://doi.org/10.1145/1008992.1009129","mag":"2070509841"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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":"https://openalex.org/A5018956134","display_name":"D. S. Hunnisett","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"D. S. Hunnisett","raw_affiliation_strings":["CORData, Parc Meni, Bangor"],"affiliations":[{"raw_affiliation_string":"CORData, Parc Meni, Bangor","institution_ids":[]}]},{"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"],"affiliations":[{"raw_affiliation_string":"University of Wales, Bangor","institution_ids":["https://openalex.org/I161548249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018956134"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8994,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80933554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"578","last_page":"579"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8729102611541748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7584749460220337},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7156351804733276},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6695382595062256},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.6648119688034058},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5378865599632263},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5317954421043396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313779711723328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5174182653427124},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5012176036834717},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4817216992378235},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4685816466808319},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3528844714164734},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3318735957145691},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2888607382774353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12021055817604065}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8729102611541748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584749460220337},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7156351804733276},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6695382595062256},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.6648119688034058},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5378865599632263},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5317954421043396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313779711723328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5174182653427124},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5012176036834717},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4817216992378235},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4685816466808319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3528844714164734},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3318735957145691},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2888607382774353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12021055817604065},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1490796714","https://openalex.org/W1974927094","https://openalex.org/W2170654002"],"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],"propose":[1],"several":[2],"context-based":[3],"methods":[4],"for":[5],"text":[6],"categorization.":[7],"One":[8],"method,":[9,35],"a":[10],"small":[11],"modification":[12],"to":[13,21],"the":[14,28,40],"PPM":[15],"compression-based":[16],"model":[17],"which":[18],"is":[19],"known":[20],"significantly":[22],"degrade":[23],"compression":[24],"performance,":[25],"counter-intuitively":[26],"has":[27],"opposite":[29],"effect":[30],"on":[31],"categorization":[32],"performance.":[33],"Another":[34],"called":[36],"C-measure,":[37],"simply":[38],"counts":[39],"presence":[41],"of":[42],"higher":[43],"order":[44],"character":[45],"contexts,":[46],"and":[47],"outperforms":[48],"all":[49],"other":[50],"approaches":[51],"investigated.":[52]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}