{"id":"https://openalex.org/W3167765143","doi":"https://doi.org/10.1109/access.2021.3086586","title":"High-Quality Train Data Generation for Deep Learning-Based Web Page Classification Models","display_name":"High-Quality Train Data Generation for Deep Learning-Based Web Page Classification Models","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3167765143","doi":"https://doi.org/10.1109/access.2021.3086586","mag":"3167765143"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3086586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3086586","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09446993.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09446993.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043354220","display_name":"Jeong-Jae Kim","orcid":"https://orcid.org/0000-0002-9629-6816"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Jae Kim","raw_affiliation_strings":["Graduate School of Cognitive Science, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9629-6816","affiliations":[{"raw_affiliation_string":"Graduate School of Cognitive Science, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084878720","display_name":"Byung-Won On","orcid":"https://orcid.org/0000-0001-6929-3188"},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byung-Won On","raw_affiliation_strings":["Kunsan National University, Gunsan, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6929-3188","affiliations":[{"raw_affiliation_string":"Kunsan National University, Gunsan, South Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101452810","display_name":"Ingyu Lee","orcid":"https://orcid.org/0000-0001-9143-6384"},"institutions":[{"id":"https://openalex.org/I149292303","display_name":"Troy University","ror":"https://ror.org/029jj9438","country_code":"US","type":"education","lineage":["https://openalex.org/I149292303"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ingyu Lee","raw_affiliation_strings":["Sorrell College of Business, Troy University, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorrell College of Business, Troy University, AL, USA","institution_ids":["https://openalex.org/I149292303"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043354220"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5599,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72755812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"85240","last_page":"85254"},"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9987999796867371,"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":0.7899181842803955},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6628814935684204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6543964147567749},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5340684056282043},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.529081404209137},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5248377919197083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42482230067253113},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3774985671043396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3245004117488861},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15211671590805054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899181842803955},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6628814935684204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6543964147567749},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5340684056282043},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.529081404209137},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5248377919197083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42482230067253113},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3774985671043396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3245004117488861},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15211671590805054},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3086586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3086586","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09446993.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fba0dcfad7c7436e978539ce34a73a80","is_oa":true,"landing_page_url":"https://doaj.org/article/fba0dcfad7c7436e978539ce34a73a80","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 85240-85254 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3086586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3086586","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09446993.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2420811182","display_name":null,"funder_award_id":"2019R1F1A1060752","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3639147631","display_name":null,"funder_award_id":"NRF-2019R1F1A1060752","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167765143.pdf","grobid_xml":"https://content.openalex.org/works/W3167765143.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W7538220","https://openalex.org/W391985582","https://openalex.org/W1834987204","https://openalex.org/W1938755728","https://openalex.org/W1940872118","https://openalex.org/W1981739849","https://openalex.org/W1988790447","https://openalex.org/W2076063813","https://openalex.org/W2144354855","https://openalex.org/W2149397822","https://openalex.org/W2156909104","https://openalex.org/W2171033594","https://openalex.org/W2246361553","https://openalex.org/W2254361154","https://openalex.org/W2269875624","https://openalex.org/W2273238862","https://openalex.org/W2463592278","https://openalex.org/W2551834456","https://openalex.org/W2760218600","https://openalex.org/W2767189351","https://openalex.org/W2794855269","https://openalex.org/W2795825100","https://openalex.org/W2896687577","https://openalex.org/W2909737018","https://openalex.org/W2909866185","https://openalex.org/W2914484425","https://openalex.org/W2921404976","https://openalex.org/W2921907837","https://openalex.org/W2945303071","https://openalex.org/W2945928904","https://openalex.org/W2951559648","https://openalex.org/W2955701345","https://openalex.org/W2959312668","https://openalex.org/W2962946486","https://openalex.org/W2963908579","https://openalex.org/W2970574105","https://openalex.org/W2975214639","https://openalex.org/W2987098737","https://openalex.org/W2995416727","https://openalex.org/W3037084154","https://openalex.org/W3089635645","https://openalex.org/W4255949318","https://openalex.org/W6600317638","https://openalex.org/W6640362995","https://openalex.org/W6640598943","https://openalex.org/W6681983783","https://openalex.org/W6691661685","https://openalex.org/W6693450727","https://openalex.org/W6767075311","https://openalex.org/W6783815107"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2731899572","https://openalex.org/W4230611425","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W3135843367","https://openalex.org/W2611741382","https://openalex.org/W4380075502","https://openalex.org/W3000197790"],"abstract_inverted_index":{"The":[0],"current":[1],"deep":[2,67],"learning":[3,68],"models":[4,69],"detecting":[5],"relevant":[6],"web":[7],"pages":[8],"show":[9,56],"low":[10],"accuracy":[11],"because":[12],"of":[13,17,39,45,65],"the":[14,18,37,40,43,58,66],"poor":[15],"quality":[16],"training":[19,33],"data.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26],"novel":[27],"algorithm":[28,79],"to":[29,82],"automatically":[30],"generate":[31],"high-quality":[32],"data":[34,54],"based":[35],"on":[36],"frequency":[38],"document":[41],"including":[42],"entity":[44],"interest.":[46],"Our":[47],"experimental":[48],"results":[49],"with":[50,76],"movies":[51],"and":[52,73],"cellphones":[53],"sets":[55],"that":[57],"average":[59],"F":[60,85],"<sub":[61,86],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[62,87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[63,88],"-score":[64],"(FNN,":[70],"CNN,":[71],"Bi-LSTM,":[72],"SeqGAN)":[74],"trained":[75],"our":[77],"proposed":[78],"shows":[80],"up":[81],"0.9992":[83],"in":[84],"-score.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}