{"id":"https://openalex.org/W2808076737","doi":"https://doi.org/10.1109/icaci.2018.8377476","title":"Designing focused crawler based on improved genetic algorithm","display_name":"Designing focused crawler based on improved genetic algorithm","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2808076737","doi":"https://doi.org/10.1109/icaci.2018.8377476","mag":"2808076737"},"language":"en","primary_location":{"id":"doi:10.1109/icaci.2018.8377476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaci.2018.8377476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Tenth International Conference on Advanced Computational Intelligence (ICACI)","raw_type":"proceedings-article"},"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/A5109032547","display_name":"Yan Wei","orcid":"https://orcid.org/0000-0002-7927-122X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yan","raw_affiliation_strings":["School of Cyber Security, Shanghai Jiao Tong University, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Security, Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003220081","display_name":"Pan Li","orcid":"https://orcid.org/0000-0003-0901-003X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Pan","raw_affiliation_strings":["School of Cyber Security, Shanghai Jiao Tong University, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Security, Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9232000112533569,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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-crawler","display_name":"Web crawler","score":0.9349918365478516},{"id":"https://openalex.org/keywords/crossover","display_name":"Crossover","score":0.7308950424194336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228968143463135},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6570391654968262},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.6175128221511841},{"id":"https://openalex.org/keywords/fitness-function","display_name":"Fitness function","score":0.6140152215957642},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5182623863220215},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.4849822521209717},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4779933989048004},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4778584837913513},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.4283784031867981},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.41903257369995117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3747705817222595},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.35787492990493774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3425472676753998},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3020678758621216},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15682724118232727},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.10954436659812927}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9349918365478516},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.7308950424194336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228968143463135},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6570391654968262},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.6175128221511841},{"id":"https://openalex.org/C176066374","wikidata":"https://www.wikidata.org/wiki/Q629118","display_name":"Fitness function","level":3,"score":0.6140152215957642},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5182623863220215},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.4849822521209717},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4779933989048004},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4778584837913513},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.4283784031867981},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.41903257369995117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3747705817222595},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.35787492990493774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425472676753998},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3020678758621216},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15682724118232727},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.10954436659812927},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaci.2018.8377476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaci.2018.8377476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Tenth International Conference on Advanced Computational Intelligence (ICACI)","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":17,"referenced_works":["https://openalex.org/W887567680","https://openalex.org/W1114377934","https://openalex.org/W1827519954","https://openalex.org/W2023070290","https://openalex.org/W2029345326","https://openalex.org/W2086074129","https://openalex.org/W2089874503","https://openalex.org/W2365051033","https://openalex.org/W2376515377","https://openalex.org/W2387844018","https://openalex.org/W2547825130","https://openalex.org/W2566714175","https://openalex.org/W2964164193","https://openalex.org/W6639140561","https://openalex.org/W6657874343","https://openalex.org/W6708982493","https://openalex.org/W6729687555"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W2102887023","https://openalex.org/W3169657889","https://openalex.org/W2964042728","https://openalex.org/W2070011826","https://openalex.org/W2390529306","https://openalex.org/W2393874032"],"abstract_inverted_index":{"As":[0],"focused":[1,38,64,150],"crawler":[2,65,151],"intends":[3],"to":[4,9,31,54],"search":[5,26,41,58,129,155],"the":[6,19,29,33,56,136,154,158],"Internet":[7],"conform":[8],"a":[10,15,63],"specific":[11],"topic,":[12],"it":[13],"has":[14],"good":[16,25],"prospect":[17],"in":[18],"field":[20],"of":[21,37,149,157],"vertical":[22],"search.":[23],"A":[24],"strategy":[27,42],"is":[28,43,84,93],"core":[30],"improve":[32,55],"accuracy":[34],"and":[35,80,90,122,147,152],"coverage":[36],"crawler.":[39,159],"Best-First":[40],"often":[44],"applied":[45],"but":[46],"easily":[47],"falls":[48],"into":[49],"local":[50],"optimization.":[51],"In":[52,71],"order":[53],"global":[57],"capability,":[59],"this":[60,72],"paper":[61],"proposes":[62],"based":[66,103],"on":[67,104],"improved":[68,96,141],"genetic":[69,134,142],"algorithm.":[70,98],"algorithm,":[73],"fitness":[74],"function":[75],"considers":[76],"both":[77],"topic":[78,91,120],"correlation":[79,83],"importance.":[81],"Topic":[82],"analyzed":[85],"by":[86,95,119],"vector":[87],"space":[88],"model":[89],"importance":[92,121],"calculated":[94],"PageRank":[97],"Genetic":[99],"operations":[100],"are":[101],"optimized":[102],"user":[105],"browsing":[106],"behavior.":[107],"Selection":[108],"operation":[109,116,124],"chooses":[110],"webpages":[111],"with":[112,132],"high":[113],"fitness,":[114],"crossover":[115],"sorts":[117],"links":[118],"mutation":[123],"searchs":[125],"combined":[126],"keywords":[127],"through":[128],"engine.":[130],"Compared":[131],"existing":[133],"algorithms,":[135],"experimental":[137],"results":[138],"show":[139],"that":[140],"algorithm":[143],"can":[144],"enhance":[145],"precision":[146],"recall":[148],"enlarge":[153],"scope":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
