{"id":"https://openalex.org/W140539934","doi":"https://doi.org/10.1007/3-540-28349-8_3","title":"Similarity-Based Text Clustering: A Comparative Study","display_name":"Similarity-Based Text Clustering: A Comparative Study","publication_year":2006,"publication_date":"2006-02-01","ids":{"openalex":"https://openalex.org/W140539934","doi":"https://doi.org/10.1007/3-540-28349-8_3","mag":"140539934"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-28349-8_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-28349-8_3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grouping Multidimensional Data","raw_type":"book-chapter"},"type":"book-chapter","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/A5103071668","display_name":"Joydeep Ghosh","orcid":"https://orcid.org/0000-0002-7366-3548"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Ghosh","raw_affiliation_strings":["Department of ECE, University of Texas at Austin, Austin, USA","University of Texas at Austin#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of ECE, University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085896252","display_name":"Alexander L. Strehl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Strehl","raw_affiliation_strings":["Nurnberg, Germany"],"affiliations":[{"raw_affiliation_string":"Nurnberg, Germany","institution_ids":["https://openalex.org/I4210100612"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103071668"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.9066,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.7201046,"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":"73","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.921999990940094,"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":0.921999990940094,"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/jaccard-index","display_name":"Jaccard index","score":0.8888733386993408},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7255327701568604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.601311206817627},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5530687570571899},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5291662216186523},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.524355411529541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5212584137916565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176315903663635},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46126797795295715},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4519517123699188},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.44128549098968506},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41505512595176697},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19084432721138},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11986032128334045},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09663605690002441}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8888733386993408},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7255327701568604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.601311206817627},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5530687570571899},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5291662216186523},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.524355411529541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5212584137916565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176315903663635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46126797795295715},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4519517123699188},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.44128549098968506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41505512595176697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19084432721138},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11986032128334045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09663605690002441}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/3-540-28349-8_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-28349-8_3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grouping Multidimensional Data","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1529516165","https://openalex.org/W3008967208","https://openalex.org/W3091428210","https://openalex.org/W3140013382","https://openalex.org/W4237625828","https://openalex.org/W2762277149","https://openalex.org/W2250135189","https://openalex.org/W2994902660","https://openalex.org/W1992869332","https://openalex.org/W4299783644"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
