{"id":"https://openalex.org/W3135570439","doi":"https://doi.org/10.1080/08874417.2020.1861571","title":"Robust Web Data Extraction Based on Weighted Path-layer Similarity","display_name":"Robust Web Data Extraction Based on Weighted Path-layer Similarity","publication_year":2021,"publication_date":"2021-03-02","ids":{"openalex":"https://openalex.org/W3135570439","doi":"https://doi.org/10.1080/08874417.2020.1861571","mag":"3135570439"},"language":"en","primary_location":{"id":"doi:10.1080/08874417.2020.1861571","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08874417.2020.1861571","pdf_url":null,"source":{"id":"https://openalex.org/S83133229","display_name":"Journal of Computer Information Systems","issn_l":"0887-4417","issn":["0887-4417","2380-2057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computer Information Systems","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/A5024596435","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0001-6331-9383"},"institutions":[{"id":"https://openalex.org/I4210118629","display_name":"NARI Group (China)","ror":"https://ror.org/02egn3136","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118629"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Laboratory of Information Security and Software Engineering, NARI Group Corporation/State Grid Electric Power Research Institute, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6331-9383","affiliations":[{"raw_affiliation_string":"Laboratory of Information Security and Software Engineering, NARI Group Corporation/State Grid Electric Power Research Institute, Nanjing, China","institution_ids":["https://openalex.org/I4210118629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102133792","display_name":"Hao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151549","display_name":"Konica Minolta (Japan)","ror":"https://ror.org/05dtvab05","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210151549"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hao Han","raw_affiliation_strings":["Konica Minolta, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Konica Minolta, Tokyo, Japan","institution_ids":["https://openalex.org/I4210151549"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024596435"],"corresponding_institution_ids":["https://openalex.org/I4210118629"],"apc_list":null,"apc_paid":null,"fwci":0.2839,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59050633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"62","issue":"3","first_page":"536","last_page":"546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9715999960899353,"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/T13976","display_name":"Web visibility and informetrics","score":0.9466000199317932,"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/robustness","display_name":"Robustness (evolution)","score":0.823948323726654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7712289094924927},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6499408483505249},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.629806399345398},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.49311205744743347},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4378720819950104},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4369237422943115},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3943856954574585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23983845114707947},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16902682185173035},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08816885948181152}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.823948323726654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712289094924927},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6499408483505249},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.629806399345398},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.49311205744743347},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4378720819950104},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4369237422943115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3943856954574585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23983845114707947},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16902682185173035},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08816885948181152},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/08874417.2020.1861571","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08874417.2020.1861571","pdf_url":null,"source":{"id":"https://openalex.org/S83133229","display_name":"Journal of Computer Information Systems","issn_l":"0887-4417","issn":["0887-4417","2380-2057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computer Information Systems","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":25,"referenced_works":["https://openalex.org/W1772106736","https://openalex.org/W1970026646","https://openalex.org/W1975255945","https://openalex.org/W1999778371","https://openalex.org/W2002956097","https://openalex.org/W2048282669","https://openalex.org/W2056112725","https://openalex.org/W2080905619","https://openalex.org/W2102189859","https://openalex.org/W2114541504","https://openalex.org/W2124157324","https://openalex.org/W2129595335","https://openalex.org/W2160189941","https://openalex.org/W2161861392","https://openalex.org/W2201534957","https://openalex.org/W2230980198","https://openalex.org/W2295645274","https://openalex.org/W2315100463","https://openalex.org/W2326804586","https://openalex.org/W2581267621","https://openalex.org/W2584049620","https://openalex.org/W2612984812","https://openalex.org/W2613027510","https://openalex.org/W2743373436","https://openalex.org/W4255952900"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W4281727072","https://openalex.org/W2560201613","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W1532073221","https://openalex.org/W2377538627","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Web":[0],"data":[1,99],"extraction":[2,19,54],"techniques":[3],"often":[4],"focus":[5],"on":[6,93],"accurate":[7],"and":[8,22,59,76],"efficient":[9],"information":[10,61],"acquisition":[11],"from":[12],"webpages.":[13],"However,":[14],"webpage":[15,75],"variants":[16,81],"cause":[17],"frequent":[18],"to":[20,32,52,84],"fail":[21],"result":[23],"in":[24,72,79],"high":[25],"maintenance":[26],"costs.":[27],"Significant":[28],"effort":[29],"is":[30,50],"attracted":[31],"robust":[33],"extraction,":[34],"but":[35],"most":[36],"either":[37],"require":[38],"complex":[39],"pre-processing":[40],"or":[41],"supplementary":[42],"files.":[43],"In":[44],"this":[45,102],"paper,":[46],"a":[47,94],"novel":[48],"method":[49,103],"proposed":[51],"enhance":[53],"robustness":[55,106],"by":[56],"using":[57],"datatype":[58],"weight":[60],"of":[62,68,97],"path-layers.":[63],"The":[64],"similarities":[65],"between":[66],"paths":[67],"the":[69,73,86,89,108],"target":[70],"node":[71,87],"original":[74],"candidate":[77],"nodes":[78],"page":[80],"are":[82],"calculated":[83],"determine":[85],"with":[88],"highest":[90],"possibility.":[91],"Experiments":[92],"large":[95],"set":[96],"real":[98],"show":[100],"that":[101],"yields":[104],"better":[105],"than":[107],"existing":[109],"approaches.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}