{"id":"https://openalex.org/W2015623780","doi":"https://doi.org/10.1145/1963192.1963249","title":"Comparative study of clustering techniques for short text documents","display_name":"Comparative study of clustering techniques for short text documents","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2015623780","doi":"https://doi.org/10.1145/1963192.1963249","mag":"2015623780"},"language":"en","primary_location":{"id":"doi:10.1145/1963192.1963249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","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/A5081380622","display_name":"Aniket Rangrej","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aniket Rangrej","raw_affiliation_strings":["IIT Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105360850","display_name":"Sayali Kulkarni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sayali Kulkarni","raw_affiliation_strings":["Self, Pune, India"],"affiliations":[{"raw_affiliation_string":"Self, Pune, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048099130","display_name":"Ashish V. Tendulkar","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish V. Tendulkar","raw_affiliation_strings":["IIT Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081380622"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":7.0162,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.96805975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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":0.998199999332428,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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":0.9968000054359436,"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/cluster-analysis","display_name":"Cluster analysis","score":0.791769802570343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634772062301636},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.6313401460647583},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5711537599563599},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5704014301300049},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.517108678817749},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.44633185863494873},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41868042945861816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3569992184638977},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3469526171684265},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3232845366001129},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18136245012283325}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.791769802570343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634772062301636},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.6313401460647583},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5711537599563599},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5704014301300049},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.517108678817749},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.44633185863494873},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41868042945861816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3569992184638977},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3469526171684265},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3232845366001129},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18136245012283325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1963192.1963249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.8473","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.8473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2011india.com/proceeding/companion/p111.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"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":7,"referenced_works":["https://openalex.org/W44927516","https://openalex.org/W1651093245","https://openalex.org/W1901600440","https://openalex.org/W2088314245","https://openalex.org/W2144927428","https://openalex.org/W2147152072","https://openalex.org/W2165232124"],"related_works":["https://openalex.org/W2362911195","https://openalex.org/W2181939267","https://openalex.org/W2149742493","https://openalex.org/W2799732470","https://openalex.org/W1966994709","https://openalex.org/W2282393731","https://openalex.org/W4226410418","https://openalex.org/W2803938633","https://openalex.org/W3217529043","https://openalex.org/W2187953929"],"abstract_inverted_index":{"We":[0,24],"compare":[1],"various":[2],"document":[3],"clustering":[4,47],"techniques":[5],"including":[6],"K-means,":[7],"SVD-based":[8],"method":[9],"and":[10,14],"a":[11,26],"graph-based":[12,39],"approach":[13,40],"their":[15],"performance":[16],"on":[17],"short":[18,48],"text":[19,49],"data":[20,50],"collected":[21],"from":[22],"Twitter.":[23],"define":[25],"measure":[27],"for":[28],"evaluating":[29],"the":[30],"cluster":[31,53],"error":[32],"with":[33,51],"these":[34],"techniques.":[35],"Observations":[36],"show":[37],"that":[38],"using":[41],"affinity":[42],"propagation":[43],"performs":[44],"best":[45],"in":[46],"minimal":[52],"error.":[54]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}