{"id":"https://openalex.org/W1585296864","doi":"https://doi.org/10.1007/978-3-540-87881-0_43","title":"A Clustering Framework to Build Focused Web Crawlers for Automatic Extraction of Cultural Information","display_name":"A Clustering Framework to Build Focused Web Crawlers for Automatic Extraction of Cultural Information","publication_year":2008,"publication_date":"2008-09-21","ids":{"openalex":"https://openalex.org/W1585296864","doi":"https://doi.org/10.1007/978-3-540-87881-0_43","mag":"1585296864"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-87881-0_43","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87881-0_43","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5084644811","display_name":"George E. Tsekouras","orcid":"https://orcid.org/0000-0001-7006-1536"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"George E. Tsekouras","raw_affiliation_strings":["Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007818641","display_name":"Damianos Gavalas","orcid":"https://orcid.org/0000-0003-4208-8613"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Damianos Gavalas","raw_affiliation_strings":["Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030797131","display_name":"Stefanos Filios","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stefanos Filios","raw_affiliation_strings":["Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022080666","display_name":"Antonios D. Niros","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Antonios D. Niros","raw_affiliation_strings":["Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006440905","display_name":"George Bafaloukas","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Bafaloukas","raw_affiliation_strings":["Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, 81100, Mytilene, Lesvos, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Cultural Technology and Communication, University of the Aegean, Lesvos, Greece 81100#TAB#","institution_ids":["https://openalex.org/I98805295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007818641","https://openalex.org/A5084644811"],"corresponding_institution_ids":["https://openalex.org/I98805295"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.5073,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57972962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"419","last_page":"424"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9455000162124634,"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":0.9397000074386597,"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/computer-science","display_name":"Computer science","score":0.8169633746147156},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6656822562217712},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6189338564872742},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6189126968383789},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6095432043075562},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6007493734359741},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.5382537245750427},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5072150230407715},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5003492832183838},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46131253242492676},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.43995389342308044},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.43661242723464966},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37119096517562866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26481783390045166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169633746147156},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6656822562217712},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6189338564872742},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6189126968383789},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6095432043075562},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6007493734359741},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.5382537245750427},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5072150230407715},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5003492832183838},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46131253242492676},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.43995389342308044},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43661242723464966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37119096517562866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26481783390045166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-87881-0_43","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87881-0_43","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1551437406","https://openalex.org/W1586077130","https://openalex.org/W2017726337","https://openalex.org/W2119426258","https://openalex.org/W2146970132","https://openalex.org/W2505805000"],"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":null,"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
