{"id":"https://openalex.org/W2137313854","doi":"https://doi.org/10.1145/1963405.1963468","title":"Highly efficient algorithms for structural clustering of large websites","display_name":"Highly efficient algorithms for structural clustering of large websites","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2137313854","doi":"https://doi.org/10.1145/1963405.1963468","mag":"2137313854"},"language":"en","primary_location":{"id":"doi:10.1145/1963405.1963468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963405.1963468","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 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/A5091733958","display_name":"Lorenzo Blanco","orcid":"https://orcid.org/0000-0003-0035-475X"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Lorenzo Blanco","raw_affiliation_strings":["Universit\u00e0 degli Studi Roma Tre, Rome, Italy","Universita degli Studi Roma Tre, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Universita degli Studi Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081323769","display_name":"Nilesh Dalvi","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":"Nilesh Dalvi","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA, USA","Yahoo! Research, Santa Clara , CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Research, Santa Clara , CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018314576","display_name":"Ashwin Machanavajjhala","orcid":"https://orcid.org/0000-0003-1555-7330"},"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":"Ashwin Machanavajjhala","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA, USA","Yahoo! Research, Santa Clara , CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Research, Santa Clara , CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091733958"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":15.2888,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98703696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"437","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9857000112533569,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9835000038146973,"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/computer-science","display_name":"Computer science","score":0.8183759450912476},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7843422889709473},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7428956031799316},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7235300540924072},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7153921127319336},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5222041010856628},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4625180959701538},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.43031591176986694},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36694127321243286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32731419801712036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23681670427322388},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21476346254348755},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13306298851966858},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.09954500198364258},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.0706167221069336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183759450912476},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7843422889709473},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7428956031799316},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7235300540924072},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7153921127319336},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5222041010856628},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4625180959701538},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.43031591176986694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36694127321243286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32731419801712036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23681670427322388},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21476346254348755},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13306298851966858},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.09954500198364258},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0706167221069336}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1963405.1963468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963405.1963468","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 on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.9374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.9374","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/proceedings/p437.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W136639676","https://openalex.org/W1553019137","https://openalex.org/W1590025341","https://openalex.org/W1599223216","https://openalex.org/W1602270052","https://openalex.org/W1971415141","https://openalex.org/W1984911948","https://openalex.org/W1993141752","https://openalex.org/W2002956097","https://openalex.org/W2023673418","https://openalex.org/W2043440779","https://openalex.org/W2047260621","https://openalex.org/W2049365470","https://openalex.org/W2049711652","https://openalex.org/W2065568440","https://openalex.org/W2101460669","https://openalex.org/W2102694093","https://openalex.org/W2103069411","https://openalex.org/W2104086170","https://openalex.org/W2128381480","https://openalex.org/W2135767707","https://openalex.org/W2139081439","https://openalex.org/W2145007893","https://openalex.org/W2148210463","https://openalex.org/W2156049581","https://openalex.org/W2160873337","https://openalex.org/W3015882749","https://openalex.org/W6633154970","https://openalex.org/W6681973738"],"related_works":["https://openalex.org/W1881353113","https://openalex.org/W2187771236","https://openalex.org/W2387616437","https://openalex.org/W1556894713","https://openalex.org/W3017141102","https://openalex.org/W2168047402","https://openalex.org/W1967149489","https://openalex.org/W2232662898","https://openalex.org/W2102444931","https://openalex.org/W3130985738"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,80],"present":[4],"a":[5,45,88],"highly":[6],"scalable":[7],"algorithm":[8],"for":[9,13],"structurally":[10],"clustering":[11],"webpages":[12,24,34],"extraction.":[14],"We":[15],"show":[16],"that,":[17],"using":[18],"only":[19],"the":[20,23,39,50,61,82],"URLs":[21],"of":[22,41,52,84],"and":[25,36,63,68],"simple":[26],"content":[27,67],"features,":[28],"it":[29],"is":[30,44],"possible":[31],"to":[32,58],"cluster":[33],"effectively":[35,59],"efficiently.":[37],"At":[38],"heart":[40],"our":[42,85],"techniques":[43],"principled":[46],"framework,":[47],"based":[48],"on":[49],"principles":[51],"information":[53],"theory,":[54],"that":[55],"allows":[56],"us":[57],"leverage":[60],"URLs,":[62],"combine":[64],"them":[65],"with":[66],"structural":[69],"properties.":[70],"Using":[71],"an":[72],"extensive":[73],"evaluation":[74],"over":[75],"several":[76],"large":[77],"full":[78],"websites,":[79],"demonstrate":[81],"effectiveness":[83],"techniques,":[86],"at":[87],"scale":[89],"unattainable":[90],"by":[91],"previous":[92],"techniques.":[93]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}