{"id":"https://openalex.org/W4312404752","doi":"https://doi.org/10.1109/access.2022.3229080","title":"Extracting the Main Content of Web Pages Using the First Impression Area","display_name":"Extracting the Main Content of Web Pages Using the First Impression Area","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312404752","doi":"https://doi.org/10.1109/access.2022.3229080"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3229080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3229080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09984637.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09984637.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077710386","display_name":"Geunseong Jung","orcid":"https://orcid.org/0000-0003-1722-4214"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geunseong Jung","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1722-4214","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673682","display_name":"Sungjae Han","orcid":"https://orcid.org/0000-0001-9387-7319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungjae Han","raw_affiliation_strings":["JEI Group, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-9387-7319","affiliations":[{"raw_affiliation_string":"JEI Group, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668564","display_name":"Hansung Kim","orcid":"https://orcid.org/0000-0003-4907-0491"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hansung Kim","raw_affiliation_strings":["Department of Sociology, Hanyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Sociology, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041607424","display_name":"Kwanguk Kim","orcid":"https://orcid.org/0000-0002-4184-2058"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanguk Kim","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4184-2058","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062763435","display_name":"Jaehyuk Cha","orcid":"https://orcid.org/0000-0003-4869-901X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyuk Cha","raw_affiliation_strings":["Department of Computer Science, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4869-901X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8584,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88978359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"129958","last_page":"129969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.9498999714851379,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9233999848365784,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77662593126297},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7565003633499146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6950118541717529},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5743528008460999},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5449515581130981},{"id":"https://openalex.org/keywords/impression","display_name":"Impression","score":0.5388562083244324},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5154446363449097},{"id":"https://openalex.org/keywords/web-browser","display_name":"Web browser","score":0.4546733796596527},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4341241419315338},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3314322233200073},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2867550253868103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09598630666732788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77662593126297},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7565003633499146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6950118541717529},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5743528008460999},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5449515581130981},{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.5388562083244324},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5154446363449097},{"id":"https://openalex.org/C2983909278","wikidata":"https://www.wikidata.org/wiki/Q6368","display_name":"Web browser","level":3,"score":0.4546733796596527},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4341241419315338},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3314322233200073},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2867550253868103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09598630666732788},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3229080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3229080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09984637.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:312866263b8f44c8b6b8849767f67de3","is_oa":true,"landing_page_url":"https://doaj.org/article/312866263b8f44c8b6b8849767f67de3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 129958-129969 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3229080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3229080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09984637.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3448951064","display_name":null,"funder_award_id":"2016R1A2B4016591","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G44117325","display_name":null,"funder_award_id":"2018R1A5A7059549","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4417803711","display_name":null,"funder_award_id":"2016R1A2B4016591","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7635653741","display_name":null,"funder_award_id":"No.2018R1A5A7059549","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8133777603","display_name":null,"funder_award_id":"2018R1A5A7059549","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312404752.pdf","grobid_xml":"https://content.openalex.org/works/W4312404752.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W60538693","https://openalex.org/W1803802947","https://openalex.org/W1972337298","https://openalex.org/W2004779840","https://openalex.org/W2076910790","https://openalex.org/W2084358158","https://openalex.org/W2114808345","https://openalex.org/W2115226476","https://openalex.org/W2120101509","https://openalex.org/W2126103897","https://openalex.org/W2144543454","https://openalex.org/W2148317291","https://openalex.org/W2158051716","https://openalex.org/W2162868126","https://openalex.org/W2224057622","https://openalex.org/W2266044552","https://openalex.org/W2274492630","https://openalex.org/W2288325333","https://openalex.org/W2588006593","https://openalex.org/W2630766512","https://openalex.org/W2703214527","https://openalex.org/W2783753704","https://openalex.org/W2900319398","https://openalex.org/W2925629331","https://openalex.org/W2964079897","https://openalex.org/W3021347373","https://openalex.org/W3033281280","https://openalex.org/W3102354094","https://openalex.org/W3109166473","https://openalex.org/W3127393508","https://openalex.org/W3149048782","https://openalex.org/W3162843419","https://openalex.org/W3163323756","https://openalex.org/W3174829772","https://openalex.org/W3175996217","https://openalex.org/W3177057043","https://openalex.org/W3215322551","https://openalex.org/W4226429814","https://openalex.org/W4238300595","https://openalex.org/W6602458123","https://openalex.org/W6638151354","https://openalex.org/W6689257785","https://openalex.org/W6693703678","https://openalex.org/W6786783157","https://openalex.org/W6803847841"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W2069679074","https://openalex.org/W4239898202","https://openalex.org/W3116613346","https://openalex.org/W1559090489","https://openalex.org/W2168047402","https://openalex.org/W2115253914","https://openalex.org/W2316185946","https://openalex.org/W2376574812","https://openalex.org/W2134058816"],"abstract_inverted_index":{"Extracting":[0],"the":[1,54,61,89,94,98,112],"main":[2,43,90,139],"content":[3,44,91,107,140],"from":[4,53,114],"a":[5,42,66,69],"web":[6,15,37,56,70,194],"page":[7,71],"is":[8],"essential":[9],"in":[10,97,167],"various":[11],"applications":[12],"such":[13],"as":[14],"crawlers":[16],"and":[17,27,50,110,122,132,137,152,181],"browser":[18],"reader":[19,135],"modes.":[20],"Existing":[21],"extraction":[22,45,141],"methods":[23,142,166],"using":[24,146],"text-based":[25],"algorithms":[26],"features":[28,52],"for":[29,35],"English":[30,169],"text":[31,154,174,187],"can":[32],"be":[33],"ineffective":[34],"non-English":[36,182],"pages.":[38,195],"This":[39],"study":[40],"proposes":[41],"method":[46,59,101,161],"that":[47,72,84,159],"obtains":[48],"visual":[49],"structural":[51,121],"rendered":[55],"page.":[57],"Our":[58],"uses":[60],"first":[62],"impression":[63],"area":[64,108,113],"(FIA),":[65],"part":[67],"of":[68],"users":[73,86],"initially":[74],"view.":[75],"In":[76],"this":[77],"area,":[78],"websites":[79],"have":[80],"applied":[81],"many":[82],"techniques":[83],"enable":[85],"to":[87,171,184],"find":[88],"easily.":[92],"Using":[93],"non-textual":[95],"properties":[96],"FIA,":[99],"our":[100,127,160],"selects":[102],"three":[103],"points":[104],"with":[105],"high":[106],"density":[109],"expands":[111],"each":[115],"point":[116],"until":[117],"it":[118],"meets":[119],"several":[120],"visual-based":[123],"conditions.":[124],"We":[125],"evaluated":[126],"method,":[128],"browsers\u2019":[129],"(Mozilla":[130],"Firefox":[131],"Google":[133],"Chrome)":[134],"modes,":[136],"existing":[138],"on":[143],"multilingual":[144],"datasets":[145],"two":[147],"measures:":[148],"Longest":[149],"Common":[150],"Subsequences":[151],"matched":[153,173,186],"blocks.":[155],"The":[156],"results":[157],"showed":[158],"performed":[162],"better":[163],"than":[164],"other":[165],"both":[168],"(up":[170,183],"46%,":[172],"blocks":[175,188],"F":[176,189],"<sub":[177,190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[178,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0.5</sub>":[179,192],")":[180,193],"42%,":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}