{"id":"https://openalex.org/W3128260846","doi":"https://doi.org/10.1145/3443279.3443290","title":"Graph and Centroid-based Word Clustering","display_name":"Graph and Centroid-based Word Clustering","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3128260846","doi":"https://doi.org/10.1145/3443279.3443290","mag":"3128260846"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","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/A5008213060","display_name":"Santipong Thaiprayoon","orcid":"https://orcid.org/0000-0003-3021-474X"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Santipong Thaiprayoon","raw_affiliation_strings":["FernUniversit\u00e4t in Hagen, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"FernUniversit\u00e4t in Hagen, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003105685","display_name":"Herwig Unger","orcid":"https://orcid.org/0000-0002-8818-3600"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Herwig Unger","raw_affiliation_strings":["FernUniversit\u00e4t in Hagen, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"FernUniversit\u00e4t in Hagen, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078419084","display_name":"Mario Kubek","orcid":"https://orcid.org/0000-0003-2641-2065"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"University of Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario Kubek","raw_affiliation_strings":["FernUniversit\u00e4t in Hagen, Hagen, Germany"],"affiliations":[{"raw_affiliation_string":"FernUniversit\u00e4t in Hagen, Hagen, Germany","institution_ids":["https://openalex.org/I120691247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008213060"],"corresponding_institution_ids":["https://openalex.org/I120691247"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77018803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994000196456909,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994000196456909,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7709599733352661},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7422923445701599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6658045053482056},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5581120252609253},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.52309250831604},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.49758461117744446},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4777190685272217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47612816095352173},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.45574378967285156},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.44523200392723083},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4358091354370117},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42448049783706665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4033859968185425},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.39333653450012207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3755282163619995},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3429791033267975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14785930514335632},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1342918872833252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709599733352661},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7422923445701599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6658045053482056},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5581120252609253},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.52309250831604},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.49758461117744446},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4777190685272217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47612816095352173},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.45574378967285156},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.44523200392723083},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4358091354370117},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42448049783706665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4033859968185425},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.39333653450012207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3755282163619995},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3429791033267975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14785930514335632},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1342918872833252},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3443279.3443290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W66373487","https://openalex.org/W184076178","https://openalex.org/W2080018251","https://openalex.org/W2110480283","https://openalex.org/W2157160123","https://openalex.org/W2517635129","https://openalex.org/W2916625203","https://openalex.org/W3028262805","https://openalex.org/W3115522112","https://openalex.org/W4243127923","https://openalex.org/W4243289952"],"related_works":["https://openalex.org/W4237492828","https://openalex.org/W2130194910","https://openalex.org/W2160785859","https://openalex.org/W2189374779","https://openalex.org/W2622412490","https://openalex.org/W1981213098","https://openalex.org/W2087424554","https://openalex.org/W2384052049","https://openalex.org/W2367205823","https://openalex.org/W4220814143"],"abstract_inverted_index":{"With":[0],"the":[1,32,45,61,74,77,90,96,116,130,135],"recent":[2],"exponential":[3],"growth":[4],"of":[5,24,34,44,76,92,150],"text":[6,25,67,155],"documents,":[7],"a":[8,18,21,41],"word":[9,49,126],"clustering":[10,80,127],"algorithm":[11,83],"is":[12,138],"an":[13],"essential":[14],"approach":[15],"for":[16],"making":[17],"reduction":[19],"in":[20,125],"huge":[22],"amount":[23],"data":[26],"and":[27,47,64,68,81,102,120,141,154],"unsupervised":[28,139],"feature":[29],"selection":[30],"on":[31,95,129],"domain":[33],"natural":[35,151],"language":[36,152],"processing.":[37],"This":[38],"paper":[39],"proposes":[40],"novel":[42],"method":[43,53,72,118,137],"graph":[46],"centroid-based":[48],"clustering.":[50],"The":[51,70,99,111],"proposed":[52,71,117,136],"aims":[54],"to":[55,84,89,147],"automatically":[56],"group":[57],"similar":[58,86],"words":[59,87,104],"into":[60,108],"same":[62],"cluster":[63],"handles":[65],"noisy":[66],"outliers.":[69],"applies":[73],"concepts":[75],"hierarchical":[78],"agglomerative":[79],"K-means":[82],"find":[85],"according":[88],"criterion":[91],"distance":[93],"range":[94],"co-occurrence":[97],"graph.":[98],"small":[100],"clusters":[101],"isolated":[103],"are":[105],"also":[106],"merged":[107],"another":[109],"cluster.":[110],"experimental":[112],"results":[113],"demonstrate":[114],"that":[115],"consistently":[119],"significantly":[121],"outperforms":[122],"state-of-the-art":[123],"baselines":[124],"algorithms":[128],"ground":[131],"truth":[132],"dataset.":[133],"Besides,":[134],"learning":[140],"generic,":[142],"which":[143],"could":[144],"be":[145],"applied":[146],"various":[148],"tasks":[149],"processing":[153],"mining.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}