{"id":"https://openalex.org/W2087166835","doi":"https://doi.org/10.1109/fskd.2012.6234295","title":"Extraction of relevant components using shallow structure of HTML documents","display_name":"Extraction of relevant components using shallow structure of HTML documents","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2087166835","doi":"https://doi.org/10.1109/fskd.2012.6234295","mag":"2087166835"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2012.6234295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th 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/A5024752776","display_name":"Jun Zeng","orcid":"https://orcid.org/0000-0003-3129-9052"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Zeng","raw_affiliation_strings":["Graduate School of Information Science, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025409280","display_name":"Brendan Flanagan","orcid":"https://orcid.org/0000-0001-7644-997X"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Brendan Flanagan","raw_affiliation_strings":["Graduate School of Information Science, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004212206","display_name":"Toshihiko Sakai","orcid":"https://orcid.org/0000-0002-7484-6944"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiko Sakai","raw_affiliation_strings":["Graduate School of Information Science, Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006267512","display_name":"Sachio Hirokawa","orcid":"https://orcid.org/0000-0002-8050-1109"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sachio Hirokawa","raw_affiliation_strings":["Research Institute for Information Technology, Kyushu University, Fukuoka, Japan","Research Institute for Information Technology, Kyushu University, Fukuoka, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Research Institute for Information Technology, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Research Institute for Information Technology, Kyushu University, Fukuoka, Japan#TAB#","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024752776"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":0.7105,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81785463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"1186","last_page":"1190"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9704999923706055,"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":0.8451904058456421},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7189105153083801},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6547147035598755},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5656856298446655},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.5492047667503357},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5018165111541748},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4342806339263916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1614331603050232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8451904058456421},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7189105153083801},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6547147035598755},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5656856298446655},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.5492047667503357},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5018165111541748},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4342806339263916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1614331603050232},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2012.6234295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2120101509","https://openalex.org/W2148449063","https://openalex.org/W2171364811","https://openalex.org/W2902482573","https://openalex.org/W6756724809"],"related_works":["https://openalex.org/W2000745862","https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W4302086745","https://openalex.org/W2626998250","https://openalex.org/W2349474629","https://openalex.org/W2138585633","https://openalex.org/W2411679502"],"abstract_inverted_index":{"As":[0],"the":[1,56,102,112,125],"amount":[2],"of":[3,35,80,105,127],"web":[4,22,66,81,97],"page":[5,23],"increases,":[6],"searching":[7],"for":[8,18,63],"semi-structured":[9],"documents":[10,24,107],"is":[11,25,70],"gaining":[12],"greater":[13],"attention.":[14],"The":[15],"traditional":[16],"approach":[17],"extracting":[19],"data":[20,34],"from":[21,94],"to":[26,40,55,88,108],"write":[27],"specialized":[28],"programs,":[29],"called":[30,121],"wrappers":[31,46],"that":[32,75],"identify":[33],"interest":[36],"and":[37,60,91,110,123],"map":[38],"them":[39,62],"some":[41],"suitable":[42],"format.":[43],"However,":[44],"developing":[45],"manually":[47],"has":[48],"many":[49,96],"well":[50],"known":[51],"shortcomings,":[52],"mainly":[53],"due":[54],"difficulty":[57],"in":[58],"writing":[59],"maintaining":[61],"continually":[64],"changing":[65],"data.":[67],"Moreover,":[68],"there":[69],"no":[71],"one":[72],"wrapper":[73],"program":[74],"can":[76],"treat":[77],"all":[78],"kinds":[79],"pages.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,116],"aim":[87],"extract":[89],"relevant":[90,113],"meaningful":[92],"snippets":[93],"as":[95,99],"pages":[98],"possible,":[100],"using":[101],"shallow":[103],"feature":[104,120],"HTML":[106],"discover":[109],"analyze":[111],"components.":[114],"Also,":[115],"introduced":[117],"a":[118,131],"new":[119],"GAP":[122,128],"verified":[124],"effectiveness":[126],"by":[129],"conducting":[130],"SVM":[132],"learning":[133],"experiment.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}