{"id":"https://openalex.org/W2090646811","doi":"https://doi.org/10.4304/jsw.7.11.262-2629","title":"A Length-variable Feature Code Based Fuzzy Duplicates Elimination Approach for Large Scale Chinese WebPages","display_name":"A Length-variable Feature Code Based Fuzzy Duplicates Elimination Approach for Large Scale Chinese WebPages","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2090646811","doi":"https://doi.org/10.4304/jsw.7.11.262-2629","mag":"2090646811"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.7.11.262-2629","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.7.11.262-2629","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-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/A5082797386","display_name":"Hongzhi Guo","orcid":"https://orcid.org/0000-0002-2503-2784"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hongzhi Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110477928","display_name":"Qingcai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028433273","display_name":"Xin Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424254","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0001-9003-4252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082797386"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1316,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90482356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973000288009644,"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":0.9973000288009644,"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/T11269","display_name":"Algorithms and Data Compression","score":0.994700014591217,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8951769471168518},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.6718089580535889},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6413524150848389},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5690361261367798},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.531288206577301},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.526847243309021},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4989967346191406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3275994062423706},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20382851362228394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06448724865913391},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.04427880048751831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8951769471168518},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.6718089580535889},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6413524150848389},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5690361261367798},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.531288206577301},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.526847243309021},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4989967346191406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3275994062423706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20382851362228394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06448724865913391},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.04427880048751831},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.7.11.262-2629","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.7.11.262-2629","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W166559453","https://openalex.org/W1518509791","https://openalex.org/W1596691921","https://openalex.org/W1742907023","https://openalex.org/W1915049489","https://openalex.org/W1968197683","https://openalex.org/W1969170652","https://openalex.org/W2057989089","https://openalex.org/W2081533422","https://openalex.org/W2091340087","https://openalex.org/W2132260434","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2349251115","https://openalex.org/W2365846567","https://openalex.org/W2369315739","https://openalex.org/W2369596073","https://openalex.org/W2381975030","https://openalex.org/W2571426116","https://openalex.org/W4285719527","https://openalex.org/W6603068576"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W3018365851","https://openalex.org/W3207484021","https://openalex.org/W2349966087","https://openalex.org/W2380341745"],"abstract_inverted_index":{"Most":[0],"of":[1,48,58,99],"the":[2,46,56,64,70,83,95],"existing":[3],"Chinese":[4,27],"webpage":[5,28,79],"duplicate":[6,29,96],"elimination":[7,30,97],"approaches":[8],"do":[9],"not":[10],"focus":[11],"on":[12,33,51,76],"noisy":[13],"and":[14,25],"fuzzy":[15],"duplicates":[16,90],"elimination.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"an":[23,38],"efficient":[24],"noise-tolerant":[26],"approach":[31,85],"based":[32],"Length-variable":[34],"Feature":[35],"Code.":[36],"First,":[37],"Independent":[39],"Extraction":[40],"Unit":[41],"is":[42,60],"defined":[43],"to":[44,68],"eliminate":[45],"impact":[47],"short":[49],"paragraphs":[50],"feature":[52],"code":[53],"extraction.":[54],"Then":[55],"concept":[57],"repeatability":[59],"introduced":[61],"by":[62],"using":[63],"longest":[65],"common":[66],"substring":[67],"enhance":[69],"noise":[71],"tolerant":[72],"capability.":[73],"Experimental":[74],"results":[75],"10":[77],"million":[78],"dataset":[80],"show":[81],"that":[82],"proposed":[84],"can":[86],"efficiently":[87],"deal":[88],"with":[89,94],"from":[91],"massive":[92],"WebPages":[93],"precision":[98],"99.03%.":[100]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
