{"id":"https://openalex.org/W3143315133","doi":"https://doi.org/10.1109/wiiatw.2007.4427573","title":"Semiautomatic Extraction of Topic Maps from Web Pages Using Clustering with Web Contents and Structure","display_name":"Semiautomatic Extraction of Topic Maps from Web Pages Using Clustering with Web Contents and Structure","publication_year":2007,"publication_date":"2007-11-01","ids":{"openalex":"https://openalex.org/W3143315133","doi":"https://doi.org/10.1109/wiiatw.2007.4427573","mag":"3143315133"},"language":"en","primary_location":{"id":"doi:10.1109/wiiatw.2007.4427573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiiatw.2007.4427573","pdf_url":null,"source":{"id":"https://openalex.org/S4363606436","display_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","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/A5050981821","display_name":"Motohiro Mase","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Motohiro Mase","raw_affiliation_strings":["Tokyo Institute of Technology, Midori, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Midori, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954161","display_name":"Seiji Yamada","orcid":"https://orcid.org/0000-0002-5907-7382"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiji Yamada","raw_affiliation_strings":["National Institute of Informatics/The Graduate University for Advanced Studies (SOKENDAIA), Chiyoda, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics/The Graduate University for Advanced Studies (SOKENDAIA), Chiyoda, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109912424","display_name":"Katsumi Nitta","orcid":"https://orcid.org/0000-0002-9018-8603"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsumi Nitta","raw_affiliation_strings":["Tokyo Institute of Technology, Midori, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Midori, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050981821"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47110809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9905999898910522,"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":0.9905999898910522,"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/T11106","display_name":"Data Management and Algorithms","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9473999738693237,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8022907972335815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747029066085815},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7659453749656677},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6903874278068542},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.6193867325782776},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5393396019935608},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4923754930496216},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48442843556404114},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4801218509674072},{"id":"https://openalex.org/keywords/web-mapping","display_name":"Web mapping","score":0.45595622062683105},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3556970953941345},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.3431171178817749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32457613945007324},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.25324660539627075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18784046173095703},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06901156902313232}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8022907972335815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747029066085815},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7659453749656677},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6903874278068542},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.6193867325782776},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5393396019935608},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4923754930496216},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48442843556404114},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4801218509674072},{"id":"https://openalex.org/C24733836","wikidata":"https://www.wikidata.org/wiki/Q649186","display_name":"Web mapping","level":4,"score":0.45595622062683105},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3556970953941345},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.3431171178817749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32457613945007324},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.25324660539627075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18784046173095703},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06901156902313232},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wiiatw.2007.4427573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiiatw.2007.4427573","pdf_url":null,"source":{"id":"https://openalex.org/S4363606436","display_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385950365","https://openalex.org/W2182629206","https://openalex.org/W2015727217","https://openalex.org/W144381034","https://openalex.org/W2183707945","https://openalex.org/W2384444869","https://openalex.org/W2080799101","https://openalex.org/W3174726539","https://openalex.org/W2375973137","https://openalex.org/W2520851676"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"a":[5,14],"method":[6],"to":[7,25,39,75,98],"semi-":[8],"automatically":[9],"extract":[10,40],"Topic":[11],"Maps":[12],"from":[13,103],"set":[15],"of":[16,44,55,61,106],"Web":[17,37,56,95],"pages.":[18],"We":[19,79,108],"introduce":[20],"the":[21,26,35,41,45,51,59,64,67,71,81,86,90,94,99,104,111],"following":[22],"two":[23],"points":[24],"existing":[27],"clustering":[28],"method:":[29],"The":[30,47],"first":[31],"is":[32,49],"merging":[33],"only":[34],"linked":[36],"pages,":[38],"underlying":[42],"relationship":[43],"topics.":[46],"second":[48],"introducing":[50],"similarity":[52],"by":[53,84],"contents":[54],"pages":[57,72,96],"and":[58,63,114],"types":[60],"links,":[62],"distance":[65],"between":[66],"directories":[68],"in":[69],"which":[70],"are":[73],"located,":[74],"generate":[76,80],"dense":[77],"clusters.":[78],"topic":[82,100,112],"map":[83,113],"assuming":[85],"clusters":[87],"as":[88,92,101],"topics,":[89],"edges":[91],"associations,":[93],"related":[97],"occurrences":[102],"result":[105],"clustering.":[107],"experimentally":[109],"extracted":[110],"evaluated":[115],"it.":[116]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}