{"id":"https://openalex.org/W3156075386","doi":"https://doi.org/10.1155/2021/5529447","title":"Web News Data Extraction Technology Based on Text Keywords","display_name":"Web News Data Extraction Technology Based on Text Keywords","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3156075386","doi":"https://doi.org/10.1155/2021/5529447","mag":"3156075386"},"language":"en","primary_location":{"id":"doi:10.1155/2021/5529447","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5529447","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/5529447.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2021/5529447.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100342357","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-7321-2288"},"institutions":[{"id":"https://openalex.org/I4210139547","display_name":"Xi'an Peihua University","ror":"https://ror.org/032fx1s95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210139547"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["School of Communication, Xi'an Peihua University, Xi'an City, China","School of Communication, Xi'an Peihua University, Xi'an City"],"affiliations":[{"raw_affiliation_string":"School of Communication, Xi'an Peihua University, Xi'an City, China","institution_ids":["https://openalex.org/I4210139547"]},{"raw_affiliation_string":"School of Communication, Xi'an Peihua University, Xi'an City","institution_ids":["https://openalex.org/I4210139547"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100342357"],"corresponding_institution_ids":["https://openalex.org/I4210139547"],"apc_list":{"value":2300,"currency":"USD","value_usd":2300},"apc_paid":{"value":2300,"currency":"USD","value_usd":2300},"fwci":0.4197,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68144755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9659000039100647,"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":0.8119136095046997},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.7890275716781616},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5341576337814331},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5067415833473206},{"id":"https://openalex.org/keywords/keyword-density","display_name":"Keyword density","score":0.5004391670227051},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.48915866017341614},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.44788193702697754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43693381547927856},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.43484726548194885},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.4206800162792206},{"id":"https://openalex.org/keywords/keyword-search","display_name":"Keyword search","score":0.2638988494873047},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20710492134094238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08035513758659363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119136095046997},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.7890275716781616},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5341576337814331},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5067415833473206},{"id":"https://openalex.org/C57560718","wikidata":"https://www.wikidata.org/wiki/Q125627","display_name":"Keyword density","level":3,"score":0.5004391670227051},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.48915866017341614},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.44788193702697754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43693381547927856},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.43484726548194885},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.4206800162792206},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.2638988494873047},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20710492134094238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08035513758659363},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1155/2021/5529447","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5529447","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/5529447.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:hin:complx:5529447","is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/complexity/2021/5529447.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:c6b7f6cfb9a24ef8b49e70b03deb1802","is_oa":true,"landing_page_url":"https://doaj.org/article/c6b7f6cfb9a24ef8b49e70b03deb1802","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2021 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2021/5529447","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5529447","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/5529447.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3156075386.pdf","grobid_xml":"https://content.openalex.org/works/W3156075386.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2317515691","https://openalex.org/W2604662095","https://openalex.org/W2731632556","https://openalex.org/W2753441287","https://openalex.org/W2757794658","https://openalex.org/W2776257468","https://openalex.org/W2794450548","https://openalex.org/W2898962309","https://openalex.org/W2900664874","https://openalex.org/W2921088878","https://openalex.org/W2922731266","https://openalex.org/W2945172815","https://openalex.org/W2964214827","https://openalex.org/W2964796363","https://openalex.org/W2973226110","https://openalex.org/W2981651290","https://openalex.org/W2990392031","https://openalex.org/W3000218271","https://openalex.org/W3001895040","https://openalex.org/W3007083472","https://openalex.org/W3013326237","https://openalex.org/W3038175416","https://openalex.org/W3091870167","https://openalex.org/W3120604781","https://openalex.org/W4244065649"],"related_works":["https://openalex.org/W2795900462","https://openalex.org/W4312516753","https://openalex.org/W2619734252","https://openalex.org/W2546291456","https://openalex.org/W1993031820","https://openalex.org/W2078192001","https://openalex.org/W2106927157","https://openalex.org/W2263707997","https://openalex.org/W137719576","https://openalex.org/W1980791782"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,8,56],"shorten":[3],"the":[4,12,28,33,40,58,63,73,91,94,105,129,132],"time":[5],"for":[6,131],"users":[7],"query":[9],"news":[10,21,30,36,115,136,139],"on":[11,81,113],"Internet,":[13],"this":[14],"paper":[15],"studies":[16],"and":[17,49,62,84,90,141],"designs":[18],"a":[19,110,122],"network":[20,114],"data":[22,116],"extraction":[23,34,43,47,52,60,107,120],"technology,":[24],"which":[25,126],"can":[26,127],"obtain":[27],"main":[29],"information":[31],"through":[32],"of":[35,75,93,135],"text":[37],"keywords.":[38],"Firstly,":[39],"TF\u2010IDF":[41,64],"keyword":[42,46,51,59,119],"algorithm,":[44,48],"TextRank":[45],"LDA":[50],"algorithm":[53,65],"are":[54,88,97],"analyzed":[55],"understand":[57],"process,":[61],"is":[66,102],"optimized":[67],"by":[68,99],"Zipf\u2019s":[69],"law.":[70],"By":[71],"introducing":[72],"idea":[74],"model":[76],"fusion,":[77],"five":[78,95],"schemes":[79,96],"based":[80],"waterfall":[82],"fusion":[83,87],"parallel":[85],"combination":[86],"designed,":[89],"effects":[92],"verified":[98],"experiments.":[100],"It":[101],"found":[103],"that":[104],"designed":[106],"technology":[108],"has":[109,121],"good":[111],"effect":[112],"extraction.":[117],"News":[118],"great":[123],"application":[124],"prospect,":[125],"provide":[128],"basis":[130],"research":[133],"fields":[134],"key":[137],"phrases,":[138],"abstracts,":[140],"so":[142],"on.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
