{"id":"https://openalex.org/W4319006533","doi":"https://doi.org/10.3390/sym15020395","title":"Contextual Embeddings-Based Web Page Categorization Using the Fine-Tune BERT Model","display_name":"Contextual Embeddings-Based Web Page Categorization Using the Fine-Tune BERT Model","publication_year":2023,"publication_date":"2023-02-02","ids":{"openalex":"https://openalex.org/W4319006533","doi":"https://doi.org/10.3390/sym15020395"},"language":"en","primary_location":{"id":"doi:10.3390/sym15020395","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15020395","pdf_url":"https://www.mdpi.com/2073-8994/15/2/395/pdf?version=1675328864","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/15/2/395/pdf?version=1675328864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057816055","display_name":"Amit Kumar Nandanwar","orcid":"https://orcid.org/0000-0003-1168-0032"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Amit Kumar Nandanwar","raw_affiliation_strings":["Computer Science & Engineering Department, Maulana Azad National Institute of Technology, Bhopal 462003, India"],"raw_orcid":"https://orcid.org/0000-0003-1168-0032","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering Department, Maulana Azad National Institute of Technology, Bhopal 462003, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032170911","display_name":"Jaytrilok Choudhary","orcid":"https://orcid.org/0000-0002-8200-7403"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jaytrilok Choudhary","raw_affiliation_strings":["Computer Science & Engineering Department, Maulana Azad National Institute of Technology, Bhopal 462003, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Engineering Department, Maulana Azad National Institute of Technology, Bhopal 462003, India","institution_ids":["https://openalex.org/I91277730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057816055"],"corresponding_institution_ids":["https://openalex.org/I91277730"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":3.9762,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94791655,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"15","issue":"2","first_page":"395","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962999820709229,"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/polysemy","display_name":"Polysemy","score":0.8210346102714539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8102682828903198},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7119687795639038},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.665402889251709},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5666483640670776},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4935976266860962},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4574543535709381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42300012707710266},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4151500463485718},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4130600094795227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3284076452255249}],"concepts":[{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.8210346102714539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102682828903198},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7119687795639038},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.665402889251709},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5666483640670776},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4935976266860962},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4574543535709381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42300012707710266},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4151500463485718},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4130600094795227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3284076452255249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym15020395","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15020395","pdf_url":"https://www.mdpi.com/2073-8994/15/2/395/pdf?version=1675328864","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:134882f779ab40239289e44d8894ce72","is_oa":false,"landing_page_url":"https://doaj.org/article/134882f779ab40239289e44d8894ce72","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 15, Iss 2, p 395 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/15/2/395/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym15020395","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym15020395","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym15020395","pdf_url":"https://www.mdpi.com/2073-8994/15/2/395/pdf?version=1675328864","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4319006533.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W78135670","https://openalex.org/W1155518287","https://openalex.org/W1482034470","https://openalex.org/W1966385142","https://openalex.org/W2008638605","https://openalex.org/W2053699633","https://openalex.org/W2059586463","https://openalex.org/W2136222411","https://openalex.org/W2250539671","https://openalex.org/W2345381140","https://openalex.org/W2601936876","https://openalex.org/W2885173995","https://openalex.org/W2896457183","https://openalex.org/W2898631146","https://openalex.org/W2901643192","https://openalex.org/W2914767245","https://openalex.org/W2991170427","https://openalex.org/W2999962654","https://openalex.org/W3001895040","https://openalex.org/W3016921356","https://openalex.org/W3069933382","https://openalex.org/W3080245411","https://openalex.org/W3097850930","https://openalex.org/W3124838391","https://openalex.org/W3129207397","https://openalex.org/W3154224177","https://openalex.org/W3156333129","https://openalex.org/W3183676217","https://openalex.org/W3193514658","https://openalex.org/W3195446130","https://openalex.org/W3197464190","https://openalex.org/W3199545413","https://openalex.org/W4220828487","https://openalex.org/W4221009332","https://openalex.org/W4224098642","https://openalex.org/W4226327328","https://openalex.org/W4231582634","https://openalex.org/W4293462507","https://openalex.org/W4308531312","https://openalex.org/W4312750750","https://openalex.org/W6799862310","https://openalex.org/W6809688602","https://openalex.org/W6810414682","https://openalex.org/W7061889560"],"related_works":["https://openalex.org/W2376040010","https://openalex.org/W2613880225","https://openalex.org/W2788559978","https://openalex.org/W2358036664","https://openalex.org/W2891304714","https://openalex.org/W4385239993","https://openalex.org/W2310152915","https://openalex.org/W4362572076","https://openalex.org/W2353131598","https://openalex.org/W2378011361"],"abstract_inverted_index":{"The":[0,19,66,151],"World":[1],"Wide":[2],"Web":[3],"has":[4],"revolutionized":[5],"the":[6,11,43,53,77,95,109,119,130,138,144,154,161,173,178,190],"way":[7],"we":[8],"live,":[9],"causing":[10,91],"number":[12],"of":[13,27,55,58,69,79,97,143,153],"web":[14,20,60,70,80,106,165],"pages":[15,49,61,71],"to":[16,23,36,47,63,117,128,182,195],"increase":[17],"exponentially.":[18],"provides":[21],"access":[22],"a":[24,73,83,89,92,125],"tremendous":[25],"amount":[26],"information,":[28],"so":[29],"it":[30],"is":[31,86,102,115],"difficult":[32],"for":[33,164],"internet":[34],"users":[35],"locate":[37],"accurate":[38],"and":[39,114,170,185,202],"useful":[40],"information":[41],"on":[42,52,199],"web.":[44],"In":[45,105],"order":[46],"categorize":[48],"accurately":[50],"based":[51,198],"queries":[54],"users,":[56],"methods":[57],"categorizing":[59],"need":[62],"be":[64],"developed.":[65],"text":[67],"content":[68],"plays":[72],"significant":[74],"role":[75],"in":[76,94],"categorization":[78],"pages.":[81],"If":[82],"word\u2019s":[84],"position":[85],"altered":[87],"within":[88],"sentence,":[90,99],"change":[93],"interpretation":[96],"that":[98],"this":[100],"phenomenon":[101],"called":[103],"polysemy.":[104],"page":[107,166],"categorization,":[108,167],"polysemy":[110,120,131],"property":[111],"causes":[112],"ambiguity":[113],"referred":[116],"as":[118],"problem.":[121],"This":[122],"paper":[123],"proposes":[124],"fine-tuned":[126,177],"model":[127,156],"solve":[129],"problem,":[132],"using":[133,160],"contextual":[134],"embeddings":[135],"created":[136],"by":[137,159],"symmetry":[139],"multi-head":[140],"encoder":[141],"layer":[142],"Bidirectional":[145],"Encoder":[146],"Representations":[147],"from":[148],"Transformers":[149],"(BERT).":[150],"effectiveness":[152],"proposed":[155,179,191],"was":[157],"evaluated":[158],"benchmark":[162],"datasets":[163],"i.e.,":[168],"WebKB":[169],"DMOZ.":[171],"Furthermore,":[172],"experiment":[174],"series":[175],"also":[176],"model\u2019s":[180,192],"hyperparameters":[181],"achieve":[183],"96.00%":[184],"84.00%":[186],"F1-Scores,":[187],"respectively,":[188],"demonstrating":[189],"importance":[193],"compared":[194],"baseline":[196],"approaches":[197],"machine":[200],"learning":[201],"deep":[203],"learning.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
