{"id":"https://openalex.org/W2246771995","doi":"https://doi.org/10.1109/fskd.2015.7382162","title":"UPCA: An efficient URL-Pattern based algorithm for accurate web page classification","display_name":"UPCA: An efficient URL-Pattern based algorithm for accurate web page classification","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2246771995","doi":"https://doi.org/10.1109/fskd.2015.7382162","mag":"2246771995"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2015.7382162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2015.7382162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","raw_type":"proceedings-article"},"type":"article","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/A5101421478","display_name":"Yiming Yang","orcid":"https://orcid.org/0000-0001-8322-607X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["University of Science and Technology of China, Anhui, Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Anhui, Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080798381","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-6447-2053"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Anhui University, Anhui, Hefei"],"affiliations":[{"raw_affiliation_string":"Anhui University, Anhui, Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015586553","display_name":"Guiquan Liu","orcid":"https://orcid.org/0000-0003-0653-3935"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiquan Liu","raw_affiliation_strings":["University of Science and Technology of China, Anhui, Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Anhui, Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China, Anhui, Hefei"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Anhui, Hefei","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101421478"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.15657672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"1475","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9979000091552734,"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":0.9943000078201294,"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":0.8491238951683044},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7129146456718445},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5722603797912598},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4860883057117462},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.46228981018066406},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45715659856796265},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4412325620651245},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.43945980072021484},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43323221802711487},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4243111312389374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3927909731864929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38253018260002136},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2418929934501648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491238951683044},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7129146456718445},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5722603797912598},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4860883057117462},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.46228981018066406},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45715659856796265},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4412325620651245},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.43945980072021484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43323221802711487},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4243111312389374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3927909731864929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38253018260002136},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2418929934501648},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2015.7382162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2015.7382162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W110420324","https://openalex.org/W1571735237","https://openalex.org/W1982530130","https://openalex.org/W1986968077","https://openalex.org/W2003471189","https://openalex.org/W2008781077","https://openalex.org/W2013316690","https://openalex.org/W2016943187","https://openalex.org/W2023374068","https://openalex.org/W2051391088","https://openalex.org/W2053458824","https://openalex.org/W2055886766","https://openalex.org/W2059586463","https://openalex.org/W2097720891","https://openalex.org/W2140018945","https://openalex.org/W2152805927","https://openalex.org/W2156772624","https://openalex.org/W2544700275","https://openalex.org/W4285719527","https://openalex.org/W6634366101","https://openalex.org/W6683162393","https://openalex.org/W6729100142"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W2083329789","https://openalex.org/W2376574812"],"abstract_inverted_index":{"With":[0],"the":[1,9,39,101,129,156,170],"explosive":[2],"growth":[3],"of":[4,31,34,103,125,179],"Web":[5,19,58,104,149],"pages":[6,59,150],"appearing":[7],"in":[8,41,96,177],"Internet":[10],"and":[11,60,76,111,138,183],"mobile":[12],"Internet,":[13],"it":[14],"is":[15,44],"quite":[16],"challenging":[17],"for":[18,37,67,92],"search":[20,42],"engines":[21,43],"to":[22,155],"provide":[23],"users":[24],"with":[25,128],"desirable":[26],"results":[27,167],"from":[28,57,142],"large":[29],"amount":[30],"data.":[32],"One":[33],"important":[35],"problems":[36],"improving":[38],"service":[40],"web":[45],"page":[46,105],"classification.":[47],"For":[48],"this":[49,97],"problem,":[50],"current":[51],"approaches":[52],"usually":[53,73],"first":[54,133],"extract":[55,139],"features":[56],"then":[61],"use":[62],"traditional":[63],"machine":[64],"learning":[65,81],"methods":[66,72],"training":[68,126],"process.":[69],"However,":[70],"these":[71],"are":[74],"time-consuming":[75],"do":[77],"not":[78,89],"take":[79],"incremental":[80,163],"into":[82],"consideration":[83],"at":[84],"all,":[85],"thus":[86],"they":[87],"may":[88],"be":[90],"suitable":[91],"online":[93],"applications.":[94],"Therefore,":[95],"paper":[98],"we":[99,132,145,159],"rethink":[100],"problem":[102],"classification":[106,181],"by":[107,151],"only":[108],"using":[109],"URLs":[110,154],"propose":[112,160],"an":[113,161],"efficient":[114,162],"Url-Pattern":[115],"based":[116],"Classification":[117],"Algorithm":[118],"(named":[119],"UPCA).":[120],"Specifically,":[121],"given":[122],"a":[123,135],"set":[124],"samples":[127],"same":[130],"label,":[131],"construct":[134],"pattern":[136],"tree":[137],"main":[140],"patterns":[141],"it.":[143],"Then":[144],"can":[146],"classify":[147],"new":[148],"matching":[152],"their":[153],"patterns.":[157],"Also,":[158],"pattern-tree":[164],"algorithm.":[165],"Experimental":[166],"show":[168],"that":[169],"proposed":[171],"approach":[172],"achieves":[173],"very":[174],"promising":[175],"performance,":[176],"terms":[178],"both":[180],"accuracy":[182],"computational":[184],"efficiency.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}