{"id":"https://openalex.org/W2088314245","doi":"https://doi.org/10.1145/1277741.1277909","title":"Clustering short texts using wikipedia","display_name":"Clustering short texts using wikipedia","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2088314245","doi":"https://doi.org/10.1145/1277741.1277909","mag":"2088314245"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in 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/A5074867889","display_name":"Somnath Banerjee","orcid":"https://orcid.org/0000-0002-4947-7649"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]},{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Somnath Banerjee","raw_affiliation_strings":["Hewlett-Packard Labs, Bangalore, India","Hewlett-Packard Laboratories, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080407571","display_name":"Krishnan Ramanathan","orcid":"https://orcid.org/0000-0001-9155-6351"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]},{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Krishnan Ramanathan","raw_affiliation_strings":["Hewlett-Packard Labs, Bangalore, India","Hewlett-Packard Laboratories, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028134056","display_name":"Ajay Gupta","orcid":"https://orcid.org/0000-0001-7881-4010"},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]},{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Ajay Gupta","raw_affiliation_strings":["Hewlett-Packard Labs, Bangalore, India","Hewlett-Packard Laboratories, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074867889"],"corresponding_institution_ids":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"],"apc_list":null,"apc_paid":null,"fwci":35.6175,"has_fulltext":false,"cited_by_count":336,"citation_normalized_percentile":{"value":0.99668359,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.8944123983383179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.791454553604126},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.7813113927841187},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6607438325881958},{"id":"https://openalex.org/keywords/information-overload","display_name":"Information overload","score":0.6380810737609863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5763072371482849},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5005714893341064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3771415948867798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28582262992858887},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1923779547214508},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08183333277702332}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8944123983383179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791454553604126},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.7813113927841187},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6607438325881958},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.6380810737609863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5763072371482849},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5005714893341064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3771415948867798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28582262992858887},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1923779547214508},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08183333277702332},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1277741.1277909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.1139","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.1139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/india/documents/papers/clusteringshorttexts.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1570542661","https://openalex.org/W2004360803","https://openalex.org/W2133517430"],"related_works":["https://openalex.org/W2249125701","https://openalex.org/W2157883966","https://openalex.org/W2357241418","https://openalex.org/W4225137864","https://openalex.org/W2473579578","https://openalex.org/W2357143896","https://openalex.org/W2081647779","https://openalex.org/W2086064646","https://openalex.org/W4205646375","https://openalex.org/W2093597205"],"abstract_inverted_index":{"Subscribers":[0],"to":[1,29,41,118],"the":[2,11,38,43,53,68,74,85,113,119],"popular":[3],"news":[4],"or":[5],"blog":[6],"feeds":[7],"(RSS/Atom)":[8],"often":[9],"face":[10],"problem":[12,31],"of":[13,24,67,83,87,107,122],"information":[14,44],"overload":[15],"as":[16,61],"these":[17],"feed":[18,39,54],"sources":[19],"usually":[20,62],"deliver":[21],"large":[22],"number":[23],"items":[25,36,51,109],"periodically.":[26],"One":[27],"solution":[28],"this":[30,77,104],"could":[32],"be":[33],"clustering":[34,88,114],"similar":[35],"in":[37],"reader":[40,55],"make":[42],"more":[45],"manageable":[46],"for":[47],"a":[48,58,64,81],"user.":[49],"Clustering":[50],"at":[52],"end":[56],"is":[57,71],"challenging":[59],"task":[60],"only":[63],"small":[65],"part":[66],"actual":[69],"article":[70],"received":[72],"through":[73],"feed.":[75],"In":[76],"paper,":[78],"we":[79],"propose":[80],"method":[82],"improving":[84],"accuracy":[86,115],"short":[89],"texts":[90],"by":[91],"enriching":[92],"their":[93],"representation":[94,106],"with":[95],"additional":[96],"features":[97],"from":[98],"Wikipedia.":[99],"Empirical":[100],"results":[101],"indicate":[102],"that":[103],"enriched":[105],"text":[108],"can":[110],"substantially":[111],"improve":[112],"when":[116],"compared":[117],"conventional":[120],"bag":[121],"words":[123],"representation.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":26},{"year":2012,"cited_by_count":24}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}