{"id":"https://openalex.org/W2147241464","doi":"https://doi.org/10.1145/1076034.1076174","title":"Using dragpushing to refine centroid text classifiers","display_name":"Using dragpushing to refine centroid text classifiers","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2147241464","doi":"https://doi.org/10.1145/1076034.1076174","mag":"2147241464"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5100511387","display_name":"Songbo Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songbo Tan","raw_affiliation_strings":["ICT, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["ICT, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059575276","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-4748-6426"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["ICT, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752081","display_name":"Hongbo Xu","orcid":"https://orcid.org/0000-0002-0258-7840"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Xu","raw_affiliation_strings":["ICT, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054898062","display_name":"Moustafa Ghanem","orcid":"https://orcid.org/0000-0001-5660-4565"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Moustafa M. Ghanem","raw_affiliation_strings":["Imperial College London, London, UK","#N#Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"#N#Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045081171","display_name":"Yike Guo","orcid":"https://orcid.org/0000-0002-3075-2161"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yike Guo","raw_affiliation_strings":["Imperial College London, London, UK","#N#Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"#N#Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2465,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.54962589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"654"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9901000261306763,"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":0.9876999855041504,"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/centroid","display_name":"Centroid","score":0.9441214203834534},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7268627882003784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7192742824554443},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7028856873512268},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5975278615951538},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5516393184661865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5392275452613831},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5256993770599365},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5013856887817383},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4875604510307312},{"id":"https://openalex.org/keywords/one-class-classification","display_name":"One-class classification","score":0.42722752690315247},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41752728819847107},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41365087032318115}],"concepts":[{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.9441214203834534},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7268627882003784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192742824554443},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7028856873512268},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5975278615951538},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5516393184661865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5392275452613831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5256993770599365},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5013856887817383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4875604510307312},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.42722752690315247},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41752728819847107},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41365087032318115},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1076034.1076174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-122592","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2005&rft.spage=653&rft.aulast=Tan&rft.aufirst=&rft.atitle=Using+DragPushing+to+refine+centroid+text+classifiers&rft.title=SIGIR+2005+-+Proceedings+of+the+28th+Annual+International+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+Retrieval","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1972640883","https://openalex.org/W2009276147","https://openalex.org/W2060216474","https://openalex.org/W2150067374","https://openalex.org/W6681982510"],"related_works":["https://openalex.org/W2357114597","https://openalex.org/W2115416187","https://openalex.org/W2131202893","https://openalex.org/W2786391746","https://openalex.org/W4381430104","https://openalex.org/W2995102745","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W2948752554","https://openalex.org/W1990237101"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,11,45,49],"novel":[3],"algorithm,":[4],"DragPushing,":[5],"for":[6,24],"automatic":[7],"text":[8],"classification.":[9],"Using":[10,31],"training":[12],"data":[13],"set,":[14],"the":[15,19,27,42,54,58,66],"algorithm":[16,70],"first":[17],"calculates":[18],"prototype":[20],"vectors,":[21],"or":[22],"centroids,":[23],"each":[25],"of":[26,44,60,96],"available":[28],"document":[29],"classes.":[30],"misclassified":[32,50,67],"examples,":[33],"it":[34],"then":[35],"iteratively":[36],"refines":[37],"these":[38],"centroids;":[39],"by":[40],"dragging":[41],"centroid":[43,59],"correct":[46],"class":[47,63],"towards":[48],"example":[51],"and":[52,75],"in":[53],"same":[55],"time":[56],"pushing":[57],"an":[61],"incorrect":[62],"away":[64],"from":[65],"example.":[68],"The":[69],"is":[71,76,92],"simple":[72],"to":[73,94],"implement":[74],"computationally":[77],"very":[78],"efficient.":[79],"Evaluation":[80],"experiments":[81],"conducted":[82],"on":[83],"two":[84],"benchmark":[85],"collections":[86],"show":[87],"that":[88,95],"its":[89],"classification":[90],"accuracy":[91],"comparable":[93],"more":[97],"complex":[98],"methods,":[99],"such":[100],"as":[101],"support":[102],"vector":[103],"machines":[104],"(SVM).":[105]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}