{"id":"https://openalex.org/W1992903090","doi":"https://doi.org/10.1109/fskd.2010.5569297","title":"A novel approach for Web data extraction based on XML encoding","display_name":"A novel approach for Web data extraction based on XML encoding","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1992903090","doi":"https://doi.org/10.1109/fskd.2010.5569297","mag":"1992903090"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2010.5569297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569297","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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/A5102979521","display_name":"Tiezheng Nie","orcid":"https://orcid.org/0000-0002-0166-1324"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiezheng Nie","raw_affiliation_strings":["Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang, China","Key Laboratory of Medical Image Computing (Northeastern University, Ministry of Education), Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Key Laboratory of Medical Image Computing (Northeastern University, Ministry of Education), Shenyang, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015251362","display_name":"Derong Shen","orcid":"https://orcid.org/0000-0003-0310-6372"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Shen","raw_affiliation_strings":["Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang, China","Key Laboratory of Medical Image Computing (Northeastern University, Ministry of Education), Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Key Laboratory of Medical Image Computing (Northeastern University, Ministry of Education), Shenyang, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China","[College of Information Science & Engineering, Northeastern University, Shenyang, CHINA]"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"[College of Information Science & Engineering, Northeastern University, Shenyang, CHINA]","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110379991","display_name":"Zhong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Shi","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China","[College of Information Science & Engineering, Northeastern University, Shenyang, CHINA]"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"[College of Information Science & Engineering, Northeastern University, Shenyang, CHINA]","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102979521"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19619423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"2417","last_page":"2421"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9660999774932861,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9549999833106995,"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":0.8603612184524536},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.645950436592102},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6107058525085449},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.6051470637321472},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.5914031863212585},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5806430578231812},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5256824493408203},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5206093788146973},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5196541547775269},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.4529232084751129},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43907126784324646},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.355183869600296},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3373018205165863},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3340376317501068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13540837168693542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603612184524536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.645950436592102},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6107058525085449},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.6051470637321472},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.5914031863212585},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5806430578231812},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5256824493408203},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5206093788146973},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5196541547775269},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.4529232084751129},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43907126784324646},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.355183869600296},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3373018205165863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3340376317501068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13540837168693542},{"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/fskd.2010.5569297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569297","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W1748877974","https://openalex.org/W1927338256","https://openalex.org/W1983736818","https://openalex.org/W2061884758","https://openalex.org/W2069388662","https://openalex.org/W2093559286","https://openalex.org/W2104086170","https://openalex.org/W2106235201","https://openalex.org/W2109464129","https://openalex.org/W2125969310","https://openalex.org/W2128341918","https://openalex.org/W2133669904","https://openalex.org/W2135479443","https://openalex.org/W2139475358","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W4232071090","https://openalex.org/W4233962457","https://openalex.org/W4250847188","https://openalex.org/W4255338640","https://openalex.org/W6633758734","https://openalex.org/W6637679570","https://openalex.org/W6675573929","https://openalex.org/W6675718519","https://openalex.org/W6680718584"],"related_works":["https://openalex.org/W1501142348","https://openalex.org/W2378161351","https://openalex.org/W2115478919","https://openalex.org/W2401139123","https://openalex.org/W2121785123","https://openalex.org/W56234146","https://openalex.org/W198049983","https://openalex.org/W2371036544","https://openalex.org/W2053173742","https://openalex.org/W2593656835"],"abstract_inverted_index":{"The":[0],"problem":[1,99],"of":[2,33,51,58,77,100],"extracting":[3],"data":[4,25,43,75,110,120],"from":[5,27,81,123],"a":[6,20,40,68,78],"Web":[7,28,42,79],"page":[8,44,80],"has":[9],"been":[10],"studied":[11],"by":[12],"many":[13],"works.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,55,96],"present":[19],"novel":[21],"approach":[22,38,117],"that":[23,115],"extracts":[24],"records":[26,76,104,121],"pages":[29],"based":[30],"on":[31],"techniques":[32],"XML":[34,47,59,65],"encoding.":[35],"Firstly,":[36],"our":[37,116],"formats":[39],"given":[41],"into":[45,67],"an":[46,107],"document.":[48],"Then":[49],"instead":[50],"using":[52],"DOM-based":[53],"approaches,":[54],"make":[56],"use":[57],"encoding":[60],"model":[61],"to":[62],"transform":[63],"the":[64,74,82,86,98],"document":[66],"linear":[69],"sequence.":[70],"Our":[71],"algorithm":[72,108],"identifies":[73],"sequence,":[83],"which":[84],"avoids":[85],"complex":[87],"matching":[88],"between":[89],"sub":[90],"trees":[91],"in":[92,103],"DOM":[93],"model.":[94],"Moreover,":[95],"address":[97],"repetitive":[101],"subparts":[102],"and":[105],"propose":[106],"for":[109],"alignment.":[111],"Experimental":[112],"results":[113],"show":[114],"can":[118],"extract":[119],"accurately":[122],"web":[124],"pages.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}