{"id":"https://openalex.org/W2894762547","doi":"https://doi.org/10.1145/3209280.3229114","title":"Improving Short Text Clustering by Similarity Matrix Sparsification","display_name":"Improving Short Text Clustering by Similarity Matrix Sparsification","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2894762547","doi":"https://doi.org/10.1145/3209280.3229114","mag":"2894762547"},"language":"en","primary_location":{"id":"doi:10.1145/3209280.3229114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","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/A5056840301","display_name":"Md Rashadul Hasan Rakib","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Md Rashadul Hasan Rakib","raw_affiliation_strings":["Dalhousie University, Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101116565","display_name":"Magdalena Jankowska","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Magdalena Jankowska","raw_affiliation_strings":["Dalhousie University, Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019738080","display_name":"Norbert Zeh","orcid":"https://orcid.org/0000-0002-0562-1629"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Norbert Zeh","raw_affiliation_strings":["Dalhousie University, Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Dalhousie University, Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056840301"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67838097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.995199978351593,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8204258680343628},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7615765333175659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711828708648682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5182383060455322},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48676228523254395},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46990200877189636},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4416758418083191},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.41994088888168335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4048226773738861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37047094106674194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25976258516311646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10618361830711365}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8204258680343628},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7615765333175659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711828708648682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182383060455322},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48676228523254395},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46990200877189636},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4416758418083191},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.41994088888168335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4048226773738861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37047094106674194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25976258516311646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10618361830711365},{"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:10.1145/3209280.3229114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"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":12,"referenced_works":["https://openalex.org/W129965406","https://openalex.org/W133424112","https://openalex.org/W1775434803","https://openalex.org/W2048195127","https://openalex.org/W2089923519","https://openalex.org/W2146577751","https://openalex.org/W2171836785","https://openalex.org/W2576754561","https://openalex.org/W2766147175","https://openalex.org/W2768113420","https://openalex.org/W2950577311","https://openalex.org/W4205807230"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Short":[0],"text":[1,21,58,76],"clustering":[2,51,77],"is":[3],"an":[4],"important":[5],"but":[6],"challenging":[7],"task.":[8],"We":[9,23],"investigate":[10],"impact":[11],"of":[12,19,44,53],"similarity":[13,45,67],"matrix":[14],"sparsification":[15,27],"on":[16],"the":[17,86],"performance":[18],"short":[20,54,75],"clustering.":[22],"show":[24],"that":[25,37],"two":[26],"methods":[28,61,73],"(the":[29],"proposed":[30],"Similarity":[31],"Distribution":[32],"based,":[33],"and":[34,82],"k-nearest":[35],"neighbors)":[36],"aim":[38],"to":[39],"retain":[40],"a":[41,63],"prescribed":[42],"number":[43],"elements":[46],"per":[47],"text,":[48],"improve":[49],"hierarchical":[50],"quality":[52],"texts":[55],"for":[56,74,79],"various":[57],"similarities.":[59],"These":[60],"using":[62],"word":[64],"embedding":[65],"based":[66],"yield":[68],"competitive":[69],"results":[70],"with":[71],"state-of-the-art":[72,88],"especially":[78],"general":[80],"domain,":[81],"are":[83],"faster":[84],"than":[85],"main":[87],"baseline.":[89]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}