{"id":"https://openalex.org/W2063384862","doi":"https://doi.org/10.1109/icmlc.2010.5580695","title":"A clustering based fast detection algorithm for large scale duplicate emails","display_name":"A clustering based fast detection algorithm for large scale duplicate emails","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2063384862","doi":"https://doi.org/10.1109/icmlc.2010.5580695","mag":"2063384862"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2010.5580695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2010.5580695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Machine Learning and Cybernetics","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/A5018668652","display_name":"Lin Sun","orcid":"https://orcid.org/0000-0001-9607-9232"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Sun","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004324294","display_name":"Bingquan Liu","orcid":"https://orcid.org/0000-0001-6352-2170"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Quan Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047681321","display_name":"Baoxun Wang","orcid":"https://orcid.org/0000-0001-8995-7543"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao-Xun Wang","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424254","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0001-9003-4252"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Long Wang","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"3270","last_page":"3274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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":0.9962999820709229,"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/T11478","display_name":"Caching and Content Delivery","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8328242301940918},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7821998000144958},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.6695477962493896},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5796776413917542},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5674046277999878},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.49194857478141785},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.47591763734817505},{"id":"https://openalex.org/keywords/hash-tree","display_name":"Hash tree","score":0.416655033826828},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.41166165471076965},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.37856408953666687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37000417709350586},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3094906508922577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19182941317558289},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16903182864189148},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09207305312156677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328242301940918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7821998000144958},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.6695477962493896},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5796776413917542},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5674046277999878},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.49194857478141785},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.47591763734817505},{"id":"https://openalex.org/C27353603","wikidata":"https://www.wikidata.org/wiki/Q16948622","display_name":"Hash tree","level":4,"score":0.416655033826828},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.41166165471076965},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.37856408953666687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37000417709350586},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3094906508922577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19182941317558289},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16903182864189148},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09207305312156677},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2010.5580695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2010.5580695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Machine Learning and Cybernetics","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":9,"referenced_works":["https://openalex.org/W88429831","https://openalex.org/W1575770195","https://openalex.org/W2057989089","https://openalex.org/W2111549955","https://openalex.org/W2149037431","https://openalex.org/W2349251115","https://openalex.org/W2379247942","https://openalex.org/W4285719527","https://openalex.org/W6634317658"],"related_works":["https://openalex.org/W1539167344","https://openalex.org/W59193048","https://openalex.org/W2046569047","https://openalex.org/W2254826453","https://openalex.org/W3197499346","https://openalex.org/W4232234733","https://openalex.org/W1997069068","https://openalex.org/W3124499836","https://openalex.org/W2026512586","https://openalex.org/W1874152622"],"abstract_inverted_index":{"Duplicate":[0],"emails,":[1],"which":[2],"exist":[3],"on":[4,55,63,98],"the":[5,30,40,48,80,82,86,104],"internet":[6],"widely":[7],"and":[8,32,44],"are":[9],"mainly":[10],"caused":[11],"by":[12,75],"mailing":[13],"lists,":[14],"not":[15],"only":[16],"waste":[17],"storage":[18],"resource":[19],"but":[20],"also":[21],"bring":[22],"users":[23],"garbage.":[24],"In":[25],"this":[26,46,56],"paper,":[27],"according":[28],"to":[29,65,78],"structure":[31],"text":[33],"feature":[34],"of":[35,42],"email,":[36],"we":[37,58],"put":[38],"forward":[39],"concept":[41],"Mail-Duplicate-Degree,":[43],"in":[45,92],"way":[47],"email":[49],"duplicate":[50,67],"is":[51],"firstly":[52],"defined.":[53],"Based":[54],"definition,":[57],"develop":[59],"an":[60],"algorithm":[61,83,105],"based":[62],"clustering":[64,94],"detect":[66],"emails.":[68],"By":[69],"introducing":[70],"a":[71,107],"hash":[72],"function":[73],"provided":[74],"TRIE":[76],"tree":[77],"optimize":[79],"efficiency,":[81],"gets":[84],"over":[85],"slow":[87],"processing":[88],"speed":[89],"problem":[90],"existing":[91],"traditional":[93],"methods.":[95],"Experimental":[96],"results":[97],"large-scale":[99],"emails":[100],"have":[101],"shown":[102],"that":[103],"has":[106],"high":[108],"precision.":[109]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}