{"id":"https://openalex.org/W2166601255","doi":"https://doi.org/10.1007/11551362_33","title":"Importance of HTML Structural Elements and Metadata in Automated Subject Classification","display_name":"Importance of HTML Structural Elements and Metadata in Automated Subject Classification","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2166601255","doi":"https://doi.org/10.1007/11551362_33","mag":"2166601255"},"language":"en","primary_location":{"id":"doi:10.1007/11551362_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11551362_33","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":"book-chapter","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/A5072826753","display_name":"Koraljka Golub","orcid":"https://orcid.org/0000-0003-4169-4777"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Koraljka Golub","raw_affiliation_strings":["Knowledge Discovery and Digital Library Research Group (KnowLib), Digital Information Systems, Department of Information Technology, Lund University, Lund, Sweden"],"affiliations":[{"raw_affiliation_string":"Knowledge Discovery and Digital Library Research Group (KnowLib), Digital Information Systems, Department of Information Technology, Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075695950","display_name":"Anders Ard\u00f6","orcid":null},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anders Ard\u00f6","raw_affiliation_strings":["Knowledge Discovery and Digital Library Research Group (KnowLib), Digital Information Systems, Department of Information Technology, Lund University, Lund, Sweden"],"affiliations":[{"raw_affiliation_string":"Knowledge Discovery and Digital Library Research Group (KnowLib), Digital Information Systems, Department of Information Technology, Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072826753"],"corresponding_institution_ids":["https://openalex.org/I187531555"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.9949,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.78584559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"368","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9926999807357788,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9921000003814697,"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":0.9416999816894531,"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/computer-science","display_name":"Computer science","score":0.8367501497268677},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.711516261100769},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6401517987251282},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5682759284973145},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4947792887687683},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4619607627391815},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4450242519378662},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4182111918926239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3271692991256714},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21803131699562073},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07361507415771484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367501497268677},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.711516261100769},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6401517987251282},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5682759284973145},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4947792887687683},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4619607627391815},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4450242519378662},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4182111918926239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3271692991256714},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21803131699562073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07361507415771484}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/11551362_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11551362_33","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.96.5329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.96.5329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.alvis.info/alvis_docs/ECDL05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1482260847","https://openalex.org/W1532285064","https://openalex.org/W1563243329","https://openalex.org/W1579160127","https://openalex.org/W1596622341","https://openalex.org/W1865438743","https://openalex.org/W1992419399","https://openalex.org/W2000900876","https://openalex.org/W2005938262","https://openalex.org/W2018311971","https://openalex.org/W2048679005","https://openalex.org/W2056022172","https://openalex.org/W2064897140","https://openalex.org/W2092689128","https://openalex.org/W2101005742","https://openalex.org/W2112335400","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2137005794","https://openalex.org/W2144288153","https://openalex.org/W4230084628"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
