{"id":"https://openalex.org/W2095710322","doi":"https://doi.org/10.1109/wse.2009.5631253","title":"Towards automatic clustering of similar pages in web applications","display_name":"Towards automatic clustering of similar pages in web applications","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2095710322","doi":"https://doi.org/10.1109/wse.2009.5631253","mag":"2095710322"},"language":"en","primary_location":{"id":"doi:10.1109/wse.2009.5631253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2009.5631253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 11th IEEE International Symposium on Web Systems Evolution","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/A5079088548","display_name":"Andrea De Lucia","orcid":"https://orcid.org/0000-0002-4238-1425"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea De Lucia","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023477042","display_name":"Michele Risi","orcid":"https://orcid.org/0000-0003-1114-3480"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Risi","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074856207","display_name":"Genoveffa Tortora","orcid":"https://orcid.org/0000-0003-4765-8371"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Genoveffa Tortora","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Salerno, Via Ponte Don Melillo, 84084, Fisciano, ITALY","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082957347","display_name":"Giuseppe Scanniello","orcid":"https://orcid.org/0000-0003-0024-7508"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Scanniello","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, University of Basilicata, Potenza, Italy","Dipartimento di Matematica e Informatica, University of Basilicata, Viale Dell'Ateneo, Macchia Romana, 85100, Potenza, ITALY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, University of Basilicata, Viale Dell'Ateneo, Macchia Romana, 85100, Potenza, ITALY","institution_ids":["https://openalex.org/I20272500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"99","last_page":"108"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958000183105469,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9926999807357788,"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":0.8102242946624756},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7598429918289185},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.7019956111907959},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5563913583755493},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5510846972465515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4980049133300781},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.45269566774368286},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4344606101512909},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4141385555267334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2618575692176819},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2558319568634033},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19909623265266418},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10415366291999817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102242946624756},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7598429918289185},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.7019956111907959},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5563913583755493},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5510846972465515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4980049133300781},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.45269566774368286},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4344606101512909},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4141385555267334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2618575692176819},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2558319568634033},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19909623265266418},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10415366291999817},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wse.2009.5631253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wse.2009.5631253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 11th IEEE International Symposium on Web Systems Evolution","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unibas.it:11563/14520","is_oa":false,"landing_page_url":"http://hdl.handle.net/11563/14520","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W106960782","https://openalex.org/W1167443665","https://openalex.org/W1500066768","https://openalex.org/W1521516843","https://openalex.org/W1522930108","https://openalex.org/W1647641001","https://openalex.org/W1647671624","https://openalex.org/W1900564928","https://openalex.org/W1967583234","https://openalex.org/W1978515398","https://openalex.org/W1992419399","https://openalex.org/W2000432226","https://openalex.org/W2052794381","https://openalex.org/W2063358702","https://openalex.org/W2067315836","https://openalex.org/W2083336425","https://openalex.org/W2096393669","https://openalex.org/W2100872652","https://openalex.org/W2103860438","https://openalex.org/W2115159475","https://openalex.org/W2115818354","https://openalex.org/W2116630138","https://openalex.org/W2119106800","https://openalex.org/W2126895866","https://openalex.org/W2147152072","https://openalex.org/W2153597081","https://openalex.org/W2160172778","https://openalex.org/W2911779492","https://openalex.org/W4242216182","https://openalex.org/W4285719527","https://openalex.org/W6627870724","https://openalex.org/W6630012415","https://openalex.org/W6631307971","https://openalex.org/W6636915900","https://openalex.org/W6677391390"],"related_works":["https://openalex.org/W2461708070","https://openalex.org/W2003932770","https://openalex.org/W4362583275","https://openalex.org/W2575897682","https://openalex.org/W2844405045","https://openalex.org/W4285090010","https://openalex.org/W4280559639","https://openalex.org/W4321609555","https://openalex.org/W1531307672","https://openalex.org/W2788104449"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5],"automatic":[6],"approach":[7,20,61],"to":[8,31,57],"group":[9],"web":[10,64],"pages":[11],"that":[12],"are":[13],"similar":[14],"at":[15],"the":[16,22,47,59],"content":[17],"level.":[18],"The":[19],"uses":[21],"Levenshtein":[23],"string":[24],"edit":[25],"distance":[26],"and":[27,35,55],"Latent":[28],"Semantic":[29],"Indexing":[30],"compute":[32],"page":[33],"dissimilarity":[34],"then":[36],"groups":[37],"them":[38],"using":[39],"iteratively":[40],"a":[41,50],"Graph-Theoretic":[42],"clustering":[43,48],"algorithm.":[44],"To":[45],"automate":[46],"process":[49],"prototype":[51],"has":[52],"been":[53],"implemented":[54],"used":[56],"assess":[58],"proposed":[60],"on":[62],"three":[63],"sites.":[65]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
