{"id":"https://openalex.org/W4391407529","doi":"https://doi.org/10.1007/978-3-031-53025-8_15","title":"Text Chunking to\u00a0Improve Website Classification","display_name":"Text Chunking to\u00a0Improve Website Classification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391407529","doi":"https://doi.org/10.1007/978-3-031-53025-8_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-53025-8_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-53025-8_15","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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/A5093530812","display_name":"Mohamed Zohir Koufi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100943","display_name":"Centre de Recherche en Sciences et Technologies de l'Information et de la Communication","ror":"https://ror.org/016wdna72","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I4210100943","https://openalex.org/I4210141980","https://openalex.org/I96226040"]},{"id":"https://openalex.org/I96226040","display_name":"Universit\u00e9 de Reims Champagne-Ardenne","ror":"https://ror.org/03hypw319","country_code":"FR","type":"education","lineage":["https://openalex.org/I96226040"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mohamed Zohir Koufi","raw_affiliation_strings":["CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France","Olfeo, Paris, France"],"affiliations":[{"raw_affiliation_string":"CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France","institution_ids":["https://openalex.org/I96226040","https://openalex.org/I4210100943"]},{"raw_affiliation_string":"Olfeo, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111951033","display_name":"Zahia Guessoum","orcid":"https://orcid.org/0000-0003-1366-8889"},"institutions":[{"id":"https://openalex.org/I4210100943","display_name":"Centre de Recherche en Sciences et Technologies de l'Information et de la Communication","ror":"https://ror.org/016wdna72","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I4210100943","https://openalex.org/I4210141980","https://openalex.org/I96226040"]},{"id":"https://openalex.org/I96226040","display_name":"Universit\u00e9 de Reims Champagne-Ardenne","ror":"https://ror.org/03hypw319","country_code":"FR","type":"education","lineage":["https://openalex.org/I96226040"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zahia Guessoum","raw_affiliation_strings":["CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France"],"affiliations":[{"raw_affiliation_string":"CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France","institution_ids":["https://openalex.org/I96226040","https://openalex.org/I4210100943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052011317","display_name":"Amor Keziou","orcid":"https://orcid.org/0000-0003-3168-8429"},"institutions":[{"id":"https://openalex.org/I4387156098","display_name":"Laboratoire de Math\u00e9matiques de Reims","ror":"https://ror.org/01xkfnd03","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4387156098","https://openalex.org/I96226040"]},{"id":"https://openalex.org/I96226040","display_name":"Universit\u00e9 de Reims Champagne-Ardenne","ror":"https://ror.org/03hypw319","country_code":"FR","type":"education","lineage":["https://openalex.org/I96226040"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Amor Keziou","raw_affiliation_strings":["LMR - UMR9008, University of Reims Champagne-Ardenne, Reims, France"],"affiliations":[{"raw_affiliation_string":"LMR - UMR9008, University of Reims Champagne-Ardenne, Reims, France","institution_ids":["https://openalex.org/I96226040","https://openalex.org/I4387156098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110242111","display_name":"Itheri Yahiaoui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100943","display_name":"Centre de Recherche en Sciences et Technologies de l'Information et de la Communication","ror":"https://ror.org/016wdna72","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I4210100943","https://openalex.org/I4210141980","https://openalex.org/I96226040"]},{"id":"https://openalex.org/I96226040","display_name":"Universit\u00e9 de Reims Champagne-Ardenne","ror":"https://ror.org/03hypw319","country_code":"FR","type":"education","lineage":["https://openalex.org/I96226040"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Itheri Yahiaoui","raw_affiliation_strings":["CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France"],"affiliations":[{"raw_affiliation_string":"CReSTIC, EA 3804, University of Reims Champagne-Ardenne, Reims, France","institution_ids":["https://openalex.org/I96226040","https://openalex.org/I4210100943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090626468","display_name":"Chlo\u00e9 Martineau","orcid":"https://orcid.org/0000-0002-4829-0102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chlo\u00e9 Martineau","raw_affiliation_strings":["Olfeo, Paris, France"],"affiliations":[{"raw_affiliation_string":"Olfeo, Paris, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093530813","display_name":"Wandrille Domin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wandrille Domin","raw_affiliation_strings":["Olfeo, Paris, France"],"affiliations":[{"raw_affiliation_string":"Olfeo, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5093530812"],"corresponding_institution_ids":["https://openalex.org/I4210100943","https://openalex.org/I96226040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.032155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9988999962806702,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9988999962806702,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9959999918937683,"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/chunking","display_name":"Chunking (psychology)","score":0.8574262857437134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6721658706665039},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5397056341171265},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.44117802381515503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4225635230541229},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.372555136680603}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8574262857437134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721658706665039},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5397056341171265},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.44117802381515503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4225635230541229},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.372555136680603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-53025-8_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-53025-8_15","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1979346351","https://openalex.org/W2010970691","https://openalex.org/W2013316690","https://openalex.org/W2037021247","https://openalex.org/W2053699633","https://openalex.org/W2059586463","https://openalex.org/W2277565140","https://openalex.org/W2964110616","https://openalex.org/W3021360715","https://openalex.org/W3033830493","https://openalex.org/W3085706036","https://openalex.org/W3106298483","https://openalex.org/W3131922516","https://openalex.org/W4248018214","https://openalex.org/W4252661582","https://openalex.org/W6600109629","https://openalex.org/W6600424091","https://openalex.org/W6604204020","https://openalex.org/W6702248584","https://openalex.org/W6739901393","https://openalex.org/W6781533629"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2358573687","https://openalex.org/W186704260","https://openalex.org/W1599450222","https://openalex.org/W1496588992","https://openalex.org/W2090755435","https://openalex.org/W266409346","https://openalex.org/W2075838610","https://openalex.org/W2184026322","https://openalex.org/W4213277595"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
