{"id":"https://openalex.org/W1974840771","doi":"https://doi.org/10.1145/1980022.1980142","title":"The effect of noise in automatic text classification","display_name":"The effect of noise in automatic text classification","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W1974840771","doi":"https://doi.org/10.1145/1980022.1980142","mag":"1974840771"},"language":"en","primary_location":{"id":"doi:10.1145/1980022.1980142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980022.1980142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference &amp; Workshop on Emerging Trends in Technology - ICWET '11","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/A5000591434","display_name":"Rahul M. Samant","orcid":"https://orcid.org/0000-0002-5158-9180"},"institutions":[{"id":"https://openalex.org/I226983648","display_name":"Narsee Monjee Institute of Management Studies","ror":"https://ror.org/04qksbm30","country_code":"IN","type":"education","lineage":["https://openalex.org/I226983648"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"R. M. Samant","raw_affiliation_strings":["MPSTME, SVKM's NMIMS, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"MPSTME, SVKM's NMIMS, Mumbai, India","institution_ids":["https://openalex.org/I226983648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002659655","display_name":"Sanjay Kumar Naazre Vittal Rao","orcid":"https://orcid.org/0009-0007-6235-9261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Rao","raw_affiliation_strings":["TIMSCDR, Thakur Inst. of Mgmt Studies"],"affiliations":[{"raw_affiliation_string":"TIMSCDR, Thakur Inst. of Mgmt Studies","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000591434"],"corresponding_institution_ids":["https://openalex.org/I226983648"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.06620288,"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":"557","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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":0.9965999722480774,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.78861004114151},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7148976922035217},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6705018877983093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4940681755542755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.492815762758255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4872221052646637},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3798084855079651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78861004114151},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7148976922035217},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6705018877983093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4940681755542755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.492815762758255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4872221052646637},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3798084855079651},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1980022.1980142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980022.1980142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference &amp; Workshop on Emerging Trends in Technology - ICWET '11","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W1537030134","https://openalex.org/W1612003148","https://openalex.org/W2010595692","https://openalex.org/W2011084371","https://openalex.org/W2028962062","https://openalex.org/W2041670430","https://openalex.org/W2066792529","https://openalex.org/W2093054814","https://openalex.org/W2099140003","https://openalex.org/W2101200183","https://openalex.org/W2122254380","https://openalex.org/W3041351009"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2105860728","https://openalex.org/W4287657826"],"abstract_inverted_index":{"Noisy":[0],"unstructured":[1],"text":[2,19,25,40,67],"is":[3,55],"common":[4],"in":[5,42],"informal":[6],"settings":[7],"such":[8],"as":[9],"on-line":[10],"chat,":[11],"SMS,":[12],"email,":[13],"newsgroups":[14],"and":[15,22,59,80],"blogs,":[16],"automatically":[17,23],"transcribed":[18],"from":[20,26,47],"speech,":[21],"recognized":[24],"printed":[27],"or":[28],"handwritten":[29],"material.":[30],"This":[31],"paper":[32,54],"focuses":[33],"on":[34,65,77],"the":[35,61,78],"issues":[36],"faced":[37],"by":[38],"automatic":[39,66],"classifiers":[41],"analyzing":[43],"noisy":[44],"documents":[45],"coming":[46],"various":[48],"sources.":[49],"The":[50],"goal":[51],"of":[52,63],"this":[53],"to":[56],"bring":[57],"out":[58],"study":[60],"effect":[62],"noise":[64,76],"classification.":[68],"We":[69],"present":[70],"detailed":[71],"experimental":[72],"results":[73],"with":[74],"simulated":[75],"Tech-TC300":[79],"20-newsgroups":[81],"benchmark":[82],"datasets.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
