{"id":"https://openalex.org/W1780726185","doi":"https://doi.org/10.1007/978-3-642-34630-9_54","title":"An Approach to Improving Quality of Crawlers Using Na\u00efve Bayes for Classifier and Hyperlink Filter","display_name":"An Approach to Improving Quality of Crawlers Using Na\u00efve Bayes for Classifier and Hyperlink Filter","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1780726185","doi":"https://doi.org/10.1007/978-3-642-34630-9_54","mag":"1780726185"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-34630-9_54","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-34630-9_54","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/A5023623750","display_name":"Huu-Thien-Tan Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huu-Thien-Tan Nguyen","raw_affiliation_strings":["Yokogawa Electric International Pte. Ltd. Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Yokogawa Electric International Pte. Ltd. Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087780953","display_name":"Duy-Khanh Le","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Duy-Khanh Le","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023623750"],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.6088,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70363658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.982699990272522,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9789000153541565,"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":0.84913170337677},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.832131564617157},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8309319019317627},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6526870727539062},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6469897031784058},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6122198104858398},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6013237833976746},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5618229508399963},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5506441593170166},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4601036310195923},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42759883403778076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38538575172424316},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3084389567375183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2918623685836792},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.22022777795791626},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.20438560843467712},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.06497037410736084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84913170337677},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.832131564617157},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8309319019317627},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6526870727539062},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6469897031784058},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6122198104858398},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6013237833976746},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5618229508399963},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5506441593170166},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4601036310195923},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42759883403778076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38538575172424316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3084389567375183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2918623685836792},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.22022777795791626},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.20438560843467712},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.06497037410736084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-34630-9_54","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-34630-9_54","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W174941419","https://openalex.org/W187984960","https://openalex.org/W653687765","https://openalex.org/W1489992655","https://openalex.org/W1508584523","https://openalex.org/W1550206324","https://openalex.org/W1906182963","https://openalex.org/W1979495886","https://openalex.org/W2005422315","https://openalex.org/W2124673015","https://openalex.org/W2160050949","https://openalex.org/W2435251607","https://openalex.org/W2482173276"],"related_works":["https://openalex.org/W2067523177","https://openalex.org/W1999267468","https://openalex.org/W4385695127","https://openalex.org/W2111427713","https://openalex.org/W2352357488","https://openalex.org/W2350986653","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W2389761961","https://openalex.org/W1999548128"],"abstract_inverted_index":null,"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
