{"id":"https://openalex.org/W2150342023","doi":"https://doi.org/10.1109/sysose.2008.4724148","title":"Information mining system design and implementation based on web crawler","display_name":"Information mining system design and implementation based on web crawler","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2150342023","doi":"https://doi.org/10.1109/sysose.2008.4724148","mag":"2150342023"},"language":"en","primary_location":{"id":"doi:10.1109/sysose.2008.4724148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sysose.2008.4724148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on System of Systems Engineering","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/A5102307832","display_name":"Shan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shan Lin","raw_affiliation_strings":["College of Information Technical Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Information Technical Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032007104","display_name":"You-meng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You-meng Li","raw_affiliation_strings":["College of Information Technical Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Information Technical Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009463088","display_name":"Qingcheng Li","orcid":"https://orcid.org/0000-0002-7859-3999"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-cheng Li","raw_affiliation_strings":["College of Information Technical Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Information Technical Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102307832"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84938428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11478","display_name":"Caching and Content Delivery","score":0.9588000178337097,"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/T11644","display_name":"Spam and Phishing Detection","score":0.958299994468689,"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-crawler","display_name":"Web crawler","score":0.9341303706169128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7679173350334167},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7675362229347229},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5868456959724426},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.5752105712890625},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5585499405860901},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.44741666316986084},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4305894672870636},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37247514724731445},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2258967161178589},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.1728914976119995}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9341303706169128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679173350334167},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7675362229347229},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5868456959724426},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.5752105712890625},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5585499405860901},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.44741666316986084},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4305894672870636},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37247514724731445},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2258967161178589},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.1728914976119995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sysose.2008.4724148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sysose.2008.4724148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on System of Systems Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1506845741","https://openalex.org/W1992787177","https://openalex.org/W2005579877","https://openalex.org/W2005677600","https://openalex.org/W2123772748","https://openalex.org/W2158418010","https://openalex.org/W2164542999","https://openalex.org/W2294632035","https://openalex.org/W2295414489"],"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/W3179424333","https://openalex.org/W4248730791"],"abstract_inverted_index":{"With":[0],"the":[1,6,13,19,29,59,62,72,83,104,108,129],"information":[2,21,32,78],"explosion":[3],"causing":[4],"by":[5],"World":[7],"Wide":[8],"Web":[9,49,65,86],"in":[10],"recent":[11],"years,":[12],"issue":[14,130],"of":[15,31,61,64,76,85,107,131],"how":[16,44,56],"to":[17,45,55,57,88,122],"execute":[18],"enormous":[20],"efficiently":[22],"at":[23,136],"a":[24,137],"reasonable":[25],"lost":[26],"has":[27],"become":[28],"concern":[30],"providers,":[33],"service":[34],"agencies":[35],"and":[36,74,117,134],"end":[37],"users.":[38],"When":[39],"many":[40],"research":[41],"focus":[42],"on":[43,82],"design":[46,73],"an":[47,77],"efficient":[48,111],"crawler,":[50],"we":[51,70],"pay":[52],"our":[53],"attention":[54],"make":[58],"best":[60],"result":[63],"crawler.":[66],"In":[67],"this":[68,125],"paper,":[69],"describe":[71,110],"implementation":[75],"mining":[79],"system":[80,126],"running":[81],"results":[84,121],"crawler":[87],"gain":[89],"more":[90],"metadata":[91],"from":[92],"unstructured":[93],"documents":[94],"for":[95,113],"focused":[96],"search":[97],"(such":[98],"as":[99],"RSS":[100],"search).":[101],"We":[102],"present":[103],"software":[105],"architecture":[106],"system,":[109],"techniques":[112],"achieving":[114],"high":[115],"performance":[116],"report":[118],"preliminary":[119],"experimental":[120],"prove":[123],"that":[124],"can":[127],"address":[128],"robustness,":[132],"flexibility":[133],"accuracy":[135],"low":[138],"cost.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
