{"id":"https://openalex.org/W2154772086","doi":"https://doi.org/10.1109/fskd.2011.6019852","title":"Construct the XQuery-based wrapper for extracting web data","display_name":"Construct the XQuery-based wrapper for extracting web data","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2154772086","doi":"https://doi.org/10.1109/fskd.2011.6019852","mag":"2154772086"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2011.6019852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2011.6019852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","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/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":"Tiezheng Nie","raw_affiliation_strings":["College of Information Science and Engineering Northeastern University Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering Northeastern University Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"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/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":["College of Information Science and Engineering Northeastern University Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering Northeastern University Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"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":["Northeastern University, Shenyang, Liaoning, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, CN","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026995541","display_name":"Yue Kou","orcid":"https://orcid.org/0000-0002-5307-4893"},"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":"Yue Kou","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, CN","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101512200","display_name":"Dan Yang","orcid":"https://orcid.org/0000-0002-3817-7333"},"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":"Dan Yang","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, CN","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18482817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1788","last_page":"1792"},"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":0.9821000099182129,"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/T11478","display_name":"Caching and Content Delivery","score":0.9796000123023987,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/xquery","display_name":"XQuery","score":0.9731655120849609},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.8895989656448364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8592848777770996},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.6745154857635498},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6439063549041748},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6428656578063965},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5386685132980347},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47940537333488464},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38857224583625793},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36756575107574463}],"concepts":[{"id":"https://openalex.org/C2780512708","wikidata":"https://www.wikidata.org/wiki/Q850661","display_name":"XQuery","level":4,"score":0.9731655120849609},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.8895989656448364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8592848777770996},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.6745154857635498},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6439063549041748},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6428656578063965},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5386685132980347},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47940537333488464},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38857224583625793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36756575107574463},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2011.6019852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2011.6019852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","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":18,"referenced_works":["https://openalex.org/W1487227972","https://openalex.org/W1988217119","https://openalex.org/W2015551056","https://openalex.org/W2034797903","https://openalex.org/W2093559286","https://openalex.org/W2094930182","https://openalex.org/W2104086170","https://openalex.org/W2106235201","https://openalex.org/W2125969310","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W4232071090","https://openalex.org/W4235592330","https://openalex.org/W4250847188","https://openalex.org/W6629070510","https://openalex.org/W6675573929","https://openalex.org/W6675718519"],"related_works":["https://openalex.org/W106453523","https://openalex.org/W4256405642","https://openalex.org/W4231075805","https://openalex.org/W2154079961","https://openalex.org/W4233448385","https://openalex.org/W2169421069","https://openalex.org/W169802313","https://openalex.org/W4205604934","https://openalex.org/W99069069","https://openalex.org/W2068852373"],"abstract_inverted_index":{"Web":[0],"pages":[1],"provide":[2],"a":[3,25,82],"large":[4],"number":[5],"of":[6,38,51],"structured":[7,75],"data,":[8],"which":[9,30,63,120],"are":[10],"required":[11],"by":[12,93],"many":[13],"advanced":[14],"applications.":[15,106],"However,":[16],"existing":[17],"works":[18],"lack":[19],"the":[20],"compatibility.":[21],"This":[22],"paper":[23],"proposes":[24],"web":[26,39,118,124],"data":[27,37,44,66,73,89,119,125],"extraction":[28],"model":[29],"builds":[31],"an":[32,57],"XQuery-based":[33],"wrapper":[34,100],"for":[35,86,104,116,123],"extracting":[36,117],"pages.":[40,53],"We":[41],"firstly":[42],"annotate":[43],"values":[45],"with":[46,74],"XPATH":[47],"in":[48],"XML":[49,68,88],"documents":[50,69],"sample":[52],"Then":[54],"we":[55,112],"design":[56],"algorithm":[58],"to":[59],"generate":[60],"XQuery":[61,80],"statements":[62],"can":[64],"extract":[65],"form":[67],"and":[70,90,97],"output":[71],"result":[72],"or":[76],"semi-structured":[77],"format.":[78],"Since":[79],"is":[81,91,114,121],"well":[83],"known":[84],"standard":[85],"operating":[87],"supported":[92],"most":[94,105],"database":[95],"systems":[96],"applications,":[98],"our":[99],"has":[101],"high":[102],"compatibility":[103],"The":[107],"experimental":[108],"results":[109],"demonstrated":[110],"approach":[111],"proposed":[113],"feasible":[115],"important":[122],"integration.":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
