{"id":"https://openalex.org/W4408092624","doi":"https://doi.org/10.1109/ants63515.2024.10898189","title":"Impact of noise in distance-based short text clustering","display_name":"Impact of noise in distance-based short text clustering","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4408092624","doi":"https://doi.org/10.1109/ants63515.2024.10898189"},"language":"en","primary_location":{"id":"doi:10.1109/ants63515.2024.10898189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants63515.2024.10898189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","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/A5104264049","display_name":"Abhradeep Datta","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhradeep Datta","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Mathematics,Guwahati,Assam,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Mathematics,Guwahati,Assam,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035002083","display_name":"Ashok Singh Sairam","orcid":"https://orcid.org/0000-0001-9527-6496"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashok Singh Sairam","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Mathematics,Guwahati,Assam,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Mathematics,Guwahati,Assam,India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104264049"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2574271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.8270000219345093,"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":0.8270000219345093,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7033787965774536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932618618011475},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6148365139961243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40871137380599976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.393624484539032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33213526010513306}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7033787965774536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932618618011475},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6148365139961243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40871137380599976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.393624484539032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33213526010513306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ants63515.2024.10898189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants63515.2024.10898189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Efficient":[0],"text":[1,47],"clustering":[2,32,79,88,144],"is":[3,34,58],"essential":[4],"for":[5,111],"applications":[6],"like":[7],"recommendation":[8],"systems,":[9],"trend":[10],"analysis,":[11],"and":[12,49,72,108,162],"user":[13],"profiling,":[14],"particularly":[15],"when":[16],"dealing":[17],"with":[18],"data":[19,92],"from":[20,127],"online":[21],"repositories":[22],"such":[23,42],"as":[24],"social":[25],"media":[26],"platforms.":[27],"However,":[28],"the":[29,38,54,59,64,84,99,117,141,151],"effectiveness":[30],"of":[31,41,53,61,86,105,119,137,146,153],"methods":[33],"significantly":[35],"impacted":[36],"by":[37,93],"inherent":[39],"challenges":[40,57],"data,":[43,65],"including":[44],"sparsity,":[45],"short":[46],"length,":[48],"unstructured":[50],"nature.":[51],"One":[52],"most":[55],"critical":[56],"prevalence":[60],"noise":[62,96,107,110,113,160],"in":[63,143,150,165],"manifested":[66],"through":[67],"slang,":[68],"emojis,":[69],"misspellings,":[70],"abbreviations,":[71],"grammatical":[73],"errors,":[74],"which":[75],"can":[76],"severely":[77],"degrade":[78],"performance.":[80],"This":[81],"research":[82],"examines":[83],"robustness":[85],"distance-based":[87],"algorithms":[89],"against":[90],"noisy":[91],"systematically":[94],"introducing":[95],"directly":[97],"into":[98,158],"text.":[100],"We":[101,115],"introduce":[102],"two":[103],"types":[104],"noise\u2013attribute":[106],"class":[109],"effective":[112],"injection.":[114],"analyze":[116],"ability":[118],"different":[120],"distance":[121,148],"measures":[122,149],"to":[123],"differentiate":[124],"meaningful":[125],"content":[126],"irrelevant":[128],"information":[129],"under":[130],"these":[131],"noise-induced":[132],"conditions.":[133],"Through":[134],"a":[135],"series":[136],"experiments,":[138],"we":[139],"evaluate":[140],"degradation":[142],"accuracy":[145],"various":[147],"presence":[152],"noise,":[154],"providing":[155],"valuable":[156],"insights":[157],"their":[159],"tolerance":[161],"practical":[163],"utility":[164],"real-world":[166],"scenarios.":[167]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}