{"id":"https://openalex.org/W2024833814","doi":"https://doi.org/10.1145/1935826.1935918","title":"Scalable clustering of news search results","display_name":"Scalable clustering of news search results","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2024833814","doi":"https://doi.org/10.1145/1935826.1935918","mag":"2024833814"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046017610","display_name":"Srinivas Vadrevu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Vadrevu","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029252731","display_name":"Choon Hui Teo","orcid":"https://orcid.org/0000-0002-5724-9478"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choon Hui Teo","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019655341","display_name":"Suju Rajan","orcid":"https://orcid.org/0009-0003-0852-989X"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suju Rajan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089487172","display_name":"Kunal Punera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Punera","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000245150","display_name":"Alexander J. Smola","orcid":"https://orcid.org/0000-0002-7963-4721"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander J. Smola","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050012027","display_name":"Zhaohui Zheng","orcid":"https://orcid.org/0000-0002-7303-4856"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohui Zheng","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":2.1401,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90371514,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"675","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8872135877609253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7955067157745361},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7019617557525635},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5683086514472961},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.556425929069519},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4948102831840515},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.49084001779556274},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.46088123321533203},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4129628837108612},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3697305917739868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21310502290725708},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19474637508392334}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8872135877609253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955067157745361},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7019617557525635},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5683086514472961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.556425929069519},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4948102831840515},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.49084001779556274},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.46088123321533203},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4129628837108612},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3697305917739868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21310502290725708},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19474637508392334}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1935826.1935918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.3075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.3075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.rsise.anu.edu.au/%7Echteo/pub/Vadetal11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.278.7106","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.278.7106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Echangyi/yahoo/wsdm11_onlineclustering.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4709","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ideal.ece.utexas.edu/~kunal/papers/wsdm2011-newsclustering.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W61501806","https://openalex.org/W192724328","https://openalex.org/W995630646","https://openalex.org/W1491393069","https://openalex.org/W1533168581","https://openalex.org/W1594128868","https://openalex.org/W1790954942","https://openalex.org/W1852582905","https://openalex.org/W1902027874","https://openalex.org/W2034230784","https://openalex.org/W2074449313","https://openalex.org/W2085030399","https://openalex.org/W2096175520","https://openalex.org/W2100958137","https://openalex.org/W2101460669","https://openalex.org/W2110441437","https://openalex.org/W2130476464","https://openalex.org/W2136171036","https://openalex.org/W2137256672","https://openalex.org/W2147717514","https://openalex.org/W2160799467","https://openalex.org/W2295665070","https://openalex.org/W2963673689","https://openalex.org/W3123545922","https://openalex.org/W6602469066","https://openalex.org/W6759150888"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W1957537378","https://openalex.org/W2087424554","https://openalex.org/W3140018618","https://openalex.org/W2101637161","https://openalex.org/W2385630304","https://openalex.org/W2353797829","https://openalex.org/W2067669858","https://openalex.org/W2152187121"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4,54],"a":[5,13,27,42,55,63,68],"system":[6,56,66,75,112],"for":[7,93],"clustering":[8,74,85,94,122],"the":[9,22,46,59,95,123],"search":[10,15,19,60,65,96,125],"results":[11,61,97,102],"of":[12,33,62,106],"news":[14,18,24,35,43,47,64,107,124],"engine.":[16],"The":[17,73,100],"interface":[20],"includes":[21],"relevant":[23],"articles":[25,48],"to":[26,41],"given":[28],"query":[29],"organized":[30,77],"in":[31,67,98,121],"terms":[32],"related":[34],"stories.":[36,52],"Here":[37],"each":[38],"cluster":[39],"corresponds":[40],"story":[44],"and":[45,70,86,116],"are":[49],"clustered":[50],"into":[51,78],"We":[53,89],"that":[57,110],"clusters":[58],"fast":[69],"scalable":[71,115],"manner.":[72],"is":[76,113],"three":[79],"components":[80],"including":[81],"offline":[82],"clustering,":[83],"incremental":[84],"realtime":[87],"clustering.":[88],"propose":[90],"novel":[91],"techniques":[92],"realtime.":[99],"experimental":[101],"with":[103],"large":[104],"collections":[105],"documents":[108],"reveal":[109],"our":[111],"both":[114],"also":[117],"achieves":[118],"good":[119],"accuracy":[120],"results.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
