{"id":"https://openalex.org/W2087473891","doi":"https://doi.org/10.1145/1516241.1516319","title":"An efficient clustering framework for relevant web information","display_name":"An efficient clustering framework for relevant web information","publication_year":2009,"publication_date":"2009-02-15","ids":{"openalex":"https://openalex.org/W2087473891","doi":"https://doi.org/10.1145/1516241.1516319","mag":"2087473891"},"language":"en","primary_location":{"id":"doi:10.1145/1516241.1516319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1516241.1516319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Ubiquitous Information Management and Communication","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/A5113900420","display_name":"Ok\u2010Ran Jeong","orcid":"https://orcid.org/0000-0003-2182-1679"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ok-Ran Jeong","raw_affiliation_strings":["Sungkyunkwan University, Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100360904","display_name":"Sang-Won Lee","orcid":"https://orcid.org/0000-0002-4206-3718"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Won Lee","raw_affiliation_strings":["Sungkyunkwan University, Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12974262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"450","last_page":"456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8487770557403564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309617638587952},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6475977897644043},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6386876106262207},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5588605403900146},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.528262734413147},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5266057252883911},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.492554247379303},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47485092282295227},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4711315333843231},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.46712738275527954},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.413381427526474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13541999459266663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12116822600364685}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8487770557403564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309617638587952},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6475977897644043},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6386876106262207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5588605403900146},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.528262734413147},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5266057252883911},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.492554247379303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47485092282295227},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4711315333843231},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.46712738275527954},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.413381427526474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13541999459266663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12116822600364685},{"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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":1,"locations":[{"id":"doi:10.1145/1516241.1516319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1516241.1516319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G865939279","display_name":null,"funder_award_id":"IITA-2008-C1090-0801-0046","funder_id":"https://openalex.org/F4320321640","funder_display_name":"Ministry of Knowledge Economy"}],"funders":[{"id":"https://openalex.org/F4320321640","display_name":"Ministry of Knowledge Economy","ror":"https://ror.org/008nkqk13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1572615921","https://openalex.org/W1971784203","https://openalex.org/W1997841190","https://openalex.org/W2066636486","https://openalex.org/W2100958137","https://openalex.org/W2145036943","https://openalex.org/W2161801074"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"As":[0],"the":[1,7,56,105],"amount":[2],"of":[3,67,97,107],"available":[4],"information":[5,19,38,58],"on":[6],"Internet":[8],"grows,":[9],"it":[10],"is":[11,21],"becoming":[12],"increasingly":[13],"difficult":[14],"for":[15,31,52],"users":[16],"to":[17,23,84,90],"find":[18,37],"that":[20,35],"relevant":[22],"their":[24],"needs.":[25],"Against":[26],"this":[27,45,79,101],"backdrop,":[28],"a":[29,49,70],"need":[30],"an":[32],"automated":[33],"tool":[34],"can":[36],"quickly":[39],"and":[40,54,75,92,103],"easily":[41],"has":[42],"surfaced.":[43],"In":[44],"paper,":[46],"we":[47,81],"propose":[48],"Clustering":[50],"Framework":[51],"crawling":[53],"clustering":[55,64,73],"necessary":[57],"from":[59],"Web":[60,87],"pages.":[61],"The":[62],"proposed":[63],"framework":[65],"consists":[66],"three":[68],"modules:":[69],"preprocessing":[71],"module,":[72],"module":[74],"community":[76],"module.":[77],"Using":[78],"framework,":[80,102],"are":[82],"able":[83],"automatically":[85],"cluster":[86],"pages":[88],"according":[89],"topic":[91],"rank":[93],"them":[94],"in":[95],"terms":[96],"relevance.":[98],"We":[99],"describe":[100],"show":[104],"results":[106],"our":[108],"preliminary":[109],"validation":[110],"work.":[111]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
