{"id":"https://openalex.org/W4391237292","doi":"https://doi.org/10.1109/ictacs59847.2023.10390524","title":"Deep Learning Approaches for Web Page Classification in Focused Crawling","display_name":"Deep Learning Approaches for Web Page Classification in Focused Crawling","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4391237292","doi":"https://doi.org/10.1109/ictacs59847.2023.10390524"},"language":"en","primary_location":{"id":"doi:10.1109/ictacs59847.2023.10390524","doi":"https://doi.org/10.1109/ictacs59847.2023.10390524","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictacs59847.2023.10390524","pdf_url":null,"source":{"id":"https://openalex.org/S4363608123","display_name":"International Conference on Technological Advancements in Computational Sciences (ICTACS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5049362742","display_name":"Dharmesh Dhabliya","orcid":"https://orcid.org/0000-0002-6340-2993","observed_orcids":["https://orcid.org/0000-0002-6340-2993"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dharmesh Dhabliya","raw_affiliation_strings":["Vishwakarma Institute of Information Technology,Department of Information Technology,Pune,India","Department of Information Technology, Vishwakarma Institute of Information Technology, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vishwakarma Institute of Information Technology,Department of Information Technology,Pune,India","institution_ids":[]},{"raw_affiliation_string":"Department of Information Technology, Vishwakarma Institute of Information Technology, Pune, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745405","display_name":"Mohammed Hussien Al-Fatlawy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259362","display_name":"Islamic University of Najaf","ror":"https://ror.org/024dzaa63","country_code":"IQ","type":"education","lineage":["https://openalex.org/I4405259362"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Mohammed Hussien Al-Fatlawy","raw_affiliation_strings":["College of Technical Engineering, The Islamic university,Najaf,Iraq","College of Technical Engineering, The Islamic university, Najaf, Iraq"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Technical Engineering, The Islamic university,Najaf,Iraq","institution_ids":["https://openalex.org/I4405259362"]},{"raw_affiliation_string":"College of Technical Engineering, The Islamic university, Najaf, Iraq","institution_ids":["https://openalex.org/I4405259362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093790916","display_name":"Bhupchand Kumhar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhupchand Kumhar","raw_affiliation_strings":["IES University,Department of Computer Science &#x0026; Engineering,Bhopal,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IES University,Department of Computer Science &#x0026; Engineering,Bhopal,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002158696","display_name":"M. Rajeswari","orcid":"https://orcid.org/0000-0003-4008-1362","observed_orcids":["https://orcid.org/0000-0003-4008-1362"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Rajeswari","raw_affiliation_strings":["Prince Shri Venkateshwara Padmavathy Engineering College,Electronics and Communication Engineering,Chennai,India","Electronics and Communication Engineering, Prince Shri Venkateshwara Padmavathy Engineering College, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince Shri Venkateshwara Padmavathy Engineering College,Electronics and Communication Engineering,Chennai,India","institution_ids":[]},{"raw_affiliation_string":"Electronics and Communication Engineering, Prince Shri Venkateshwara Padmavathy Engineering College, Chennai, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067775969","display_name":"N. Kalyana Sundaram","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Kalyana Sundaram","raw_affiliation_strings":["New Prince Shri Bhavani College of Engineering and Technology,Department of Computer Science &#x0026; Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Prince Shri Bhavani College of Engineering and Technology,Department of Computer Science &#x0026; Engineering,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24822005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"725","last_page":"731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9609000086784363,"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":0.9609000086784363,"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":0.02539999969303608,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00930000003427267,"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-classification","display_name":"web page classification","score":0.9769999980926514},{"id":"https://openalex.org/keywords/focused-crawling","display_name":"focused crawling","score":0.9929999709129333},{"id":"https://openalex.org/keywords/deep-learning-architectures","display_name":"deep learning architectures","score":0.8069999814033508},{"id":"https://openalex.org/keywords/web-page-relevance","display_name":"web page relevance","score":0.3619999885559082},{"id":"https://openalex.org/keywords/training-strategies","display_name":"training strategies","score":0.7459999918937683},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.9580000042915344}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8949680328369141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877684235572815},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.718467116355896},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5321264266967773},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5271494388580322},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5188247561454773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.474136084318161},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4251399636268616},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3864585757255554},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictacs59847.2023.10390524","doi":"https://doi.org/10.1109/ictacs59847.2023.10390524","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictacs59847.2023.10390524","pdf_url":null,"source":{"id":"https://openalex.org/S4363608123","display_name":"International Conference on Technological Advancements in Computational Sciences (ICTACS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1501777393","https://openalex.org/W1927406451","https://openalex.org/W2923183845","https://openalex.org/W2955974923","https://openalex.org/W3036989029","https://openalex.org/W3186425414"],"related_works":["https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W4317382653","https://openalex.org/W3119324922","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Web":[0],"page":[1,60],"classification":[2,61],"plays":[3],"a":[4],"crucial":[5],"role":[6],"in":[7,34,62,77,90],"focused":[8,63],"crawling,":[9],"where":[10],"the":[11,85],"goal":[12],"is":[13],"to":[14,38,41],"selectively":[15],"retrieve":[16],"relevant":[17],"pages":[18],"based":[19],"on":[20],"specific":[21],"topics":[22],"or":[23],"domains":[24],"of":[25,53],"interest.":[26],"Deep":[27],"learning":[28,55,69],"approaches":[29],"have":[30],"gained":[31],"significant":[32],"attention":[33],"recent":[35],"years":[36],"due":[37],"their":[39],"ability":[40],"extract":[42],"high-level":[43],"representations":[44],"from":[45],"raw":[46],"data.":[47],"This":[48],"paper":[49],"presents":[50],"an":[51],"overview":[52],"deep":[54,68],"techniques":[56],"used":[57],"for":[58],"web":[59],"crawling.":[64],"We":[65],"discuss":[66],"various":[67],"architectures,":[70],"training":[71],"strategies,":[72],"and":[73,87],"evaluation":[74],"metrics":[75],"employed":[76],"this":[78,91],"context.":[79],"Furthermore,":[80],"we":[81],"provide":[82],"insights":[83],"into":[84],"challenges":[86],"future":[88],"directions":[89],"rapidly":[92],"evolving":[93],"field.":[94]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}
