{"id":"https://openalex.org/W2045370125","doi":"https://doi.org/10.1145/253168.253200","title":"Hierarchic document classification using Ward's clustering method","display_name":"Hierarchic document classification using Ward's clustering method","publication_year":1986,"publication_date":"1986-01-01","ids":{"openalex":"https://openalex.org/W2045370125","doi":"https://doi.org/10.1145/253168.253200","mag":"2045370125"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/253168.253200","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/253168.253200","source":{"id":"https://openalex.org/S4363609015","display_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/253168.253200","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048751805","display_name":"Abdelmoula El-Hamdouchi","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. El-Hamdouchi","raw_affiliation_strings":["Sheffield University, Western Bank, Sheffield, S10 2TN, UK"],"affiliations":[{"raw_affiliation_string":"Sheffield University, Western Bank, Sheffield, S10 2TN, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102885255","display_name":"Peter Willett","orcid":"https://orcid.org/0000-0003-4591-7173"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. Willett","raw_affiliation_strings":["Sheffield University, Western Bank, Sheffield, S10 2TN, UK"],"affiliations":[{"raw_affiliation_string":"Sheffield University, Western Bank, Sheffield, S10 2TN, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.435,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":65,"citation_normalized_percentile":{"value":0.9,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9999,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9999,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9936,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9851,"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/heuristics","display_name":"Heuristics","score":0.64270294},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document Clustering","score":0.5816809},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4522243}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.84043556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739216},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.64270294},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5816809},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5785691},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.502254},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.48319474},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.46904284},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.464091},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.46265703},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4522243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42577428},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.42420048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40824452},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/253168.253200","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/253168.253200","source":{"id":"https://openalex.org/S4363609015","display_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/253168.253200","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/253168.253200","source":{"id":"https://openalex.org/S4363609015","display_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":9,"referenced_works":["https://openalex.org/W1956559956","https://openalex.org/W2007995029","https://openalex.org/W2024668293","https://openalex.org/W2024766881","https://openalex.org/W2036372642","https://openalex.org/W2041565863","https://openalex.org/W2058272948","https://openalex.org/W2066807428","https://openalex.org/W2141807666"],"related_works":["https://openalex.org/W3120229345","https://openalex.org/W2559422900","https://openalex.org/W2374506950","https://openalex.org/W2360225591","https://openalex.org/W2342518500","https://openalex.org/W2188840951","https://openalex.org/W2171610853","https://openalex.org/W2160785859","https://openalex.org/W2103650652","https://openalex.org/W2101637161"],"abstract_inverted_index":{"In":[0],"this":[1,36],"paper,":[2],"we":[3],"discuss":[4],"the":[5,14,27,83,86],"application":[6],"of":[7,17,19,31,44,70,78,85],"a":[8,42],"recent":[9],"hierarchic":[10,23,71],"clustering":[11,24,55],"algorithm":[12,38,88],"to":[13,53,64,93],"automatic":[15],"classification":[16],"files":[18],"documents.":[20],"Whereas":[21],"most":[22],"algorithms":[25],"involve":[26],"generation":[28],"and":[29],"updating":[30],"an":[32,49],"inter-object":[33],"dissimilarity":[34],"matrix,":[35],"new":[37,87],"is":[39,51,76,91],"based":[40],"upon":[41],"series":[43],"nearest":[45],"neighbor":[46],"searches.":[47],"Such":[48],"approach":[50],"appropriate":[52],"several":[54],"methods,":[56],"including":[57],"Ward's":[58,99],"method":[59],"which":[60,80],"has":[61],"been":[62],"shown":[63],"perform":[65],"well":[66],"in":[67],"experimental":[68],"studies":[69],"document":[72,96],"clustering.":[73],"A":[74],"description":[75],"given":[77],"heuristics":[79],"can":[81],"increase":[82],"efficiency":[84],"when":[89],"it":[90],"used":[92],"cluster":[94],"three":[95],"collections":[97],"by":[98],"method.":[100]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2045370125","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-01-08T04:23:31.726863","created_date":"2016-06-24"}