{"id":"https://openalex.org/W2783443613","doi":"https://doi.org/10.1109/icsai.2017.8248509","title":"Improved KNN text classification algorithm with MapReduce implementation","display_name":"Improved KNN text classification algorithm with MapReduce implementation","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2783443613","doi":"https://doi.org/10.1109/icsai.2017.8248509","mag":"2783443613"},"language":"en","primary_location":{"id":"doi:10.1109/icsai.2017.8248509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2017.8248509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 4th International Conference on Systems and Informatics (ICSAI)","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/A5053490763","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0002-5319-0202"},"institutions":[{"id":"https://openalex.org/I4210091712","display_name":"Zhengzhou University of Science and Technology","ror":"https://ror.org/00b3j7936","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210091712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I4210091712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460972","display_name":"Yun Qian","orcid":"https://orcid.org/0000-0003-3230-5506"},"institutions":[{"id":"https://openalex.org/I4210091712","display_name":"Zhengzhou University of Science and Technology","ror":"https://ror.org/00b3j7936","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210091712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Qian","raw_affiliation_strings":["School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I4210091712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101663571","display_name":"Cui-Xia Li","orcid":"https://orcid.org/0000-0001-7230-1222"},"institutions":[{"id":"https://openalex.org/I4210091712","display_name":"Zhengzhou University of Science and Technology","ror":"https://ror.org/00b3j7936","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210091712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuixia Li","raw_affiliation_strings":["School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology and Applied Science, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I4210091712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053490763"],"corresponding_institution_ids":["https://openalex.org/I4210091712"],"apc_list":null,"apc_paid":null,"fwci":4.3526,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95276498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1417","last_page":"1422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9695000052452087,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9695000052452087,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.964900016784668,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9375,"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":0.8419628739356995},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7277905344963074},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6213008165359497},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.578156054019928},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.528967559337616},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5236199498176575},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5102653503417969},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47275763750076294},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.41212669014930725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4017123281955719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3402828574180603},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3326570987701416},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13266512751579285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419628739356995},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7277905344963074},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6213008165359497},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.578156054019928},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.528967559337616},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5236199498176575},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5102653503417969},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47275763750076294},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.41212669014930725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017123281955719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402828574180603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3326570987701416},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13266512751579285},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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:10.1109/icsai.2017.8248509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2017.8248509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 4th International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W1736726159","https://openalex.org/W2020694521","https://openalex.org/W2129473238","https://openalex.org/W2381588994"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W2757182831","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2132996594","https://openalex.org/W2158177428","https://openalex.org/W4312458517"],"abstract_inverted_index":{"The":[0,61],"classic":[1],"K-Nearest":[2],"Neighbor":[3],"(KNN)":[4],"classification":[5,21,30,76],"algorithm":[6,18,41,55,68],"is":[7,46],"widely":[8],"used":[9],"in":[10],"text":[11,20,29],"classification.":[12],"This":[13],"paper":[14],"proposes":[15],"an":[16],"efficient":[17],"for":[19],"by":[22],"improving":[23],"the":[24,34,39,43,50,53,66,75,81],"traditional":[25],"TF-IDF":[26],"based":[27],"KNN":[28,54],"algorithm.":[31],"In":[32],"addition,":[33],"MapReduce":[35,71],"parallel":[36],"implementation":[37],"of":[38,52,83],"new":[40,67],"on":[42],"Hadoop":[44],"platform":[45],"introduced":[47],"to":[48,56],"improve":[49],"capacity":[51],"process":[57],"large":[58],"data":[59],"sets.":[60],"experimental":[62],"results":[63],"show":[64],"that":[65],"implemented":[69],"through":[70],"not":[72],"only":[73],"improves":[74],"accuracy,":[77],"but":[78],"also":[79],"has":[80],"advantages":[82],"fast":[84],"convergence":[85],"and":[86],"good":[87],"scalability.":[88]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}