{"id":"https://openalex.org/W2188184094","doi":"https://doi.org/10.1109/dsaa.2015.7344829","title":"A text block context informations based multiple Web contents extraction","display_name":"A text block context informations based multiple Web contents extraction","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2188184094","doi":"https://doi.org/10.1109/dsaa.2015.7344829","mag":"2188184094"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa.2015.7344829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2015.7344829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","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/A5110572265","display_name":"Won-Moon Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wonmoon Song","raw_affiliation_strings":["Strategic Business Team ONYCOM, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Strategic Business Team ONYCOM, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113748110","display_name":"Myung-Won Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myungwon Kim","raw_affiliation_strings":["Dept. of Computing, Soongsil University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Soongsil University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110572265"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12046686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9851999878883362,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9736999869346619,"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":0.8524978160858154},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.748747706413269},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6580411791801453},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6322010159492493},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5876256227493286},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4763067960739136},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4760344326496124},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45040589570999146},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4482640027999878},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4143928587436676},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40762490034103394},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35010606050491333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07309797406196594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8524978160858154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.748747706413269},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6580411791801453},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6322010159492493},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5876256227493286},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4763067960739136},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4760344326496124},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45040589570999146},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4482640027999878},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4143928587436676},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40762490034103394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35010606050491333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07309797406196594},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa.2015.7344829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa.2015.7344829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334880","display_name":"Small and Medium Business Administration","ror":"https://ror.org/022c4zk48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W69749311","https://openalex.org/W1570448133","https://openalex.org/W1803802947","https://openalex.org/W2018107982","https://openalex.org/W2019577381","https://openalex.org/W2076665947","https://openalex.org/W2087406717","https://openalex.org/W2120101509","https://openalex.org/W2140190241","https://openalex.org/W2140208587","https://openalex.org/W3124355156","https://openalex.org/W6634094483","https://openalex.org/W6638151354","https://openalex.org/W6680704940","https://openalex.org/W6789535721"],"related_works":["https://openalex.org/W2083329789","https://openalex.org/W36911888","https://openalex.org/W2376574812","https://openalex.org/W4385731361","https://openalex.org/W2371661150","https://openalex.org/W2389795557","https://openalex.org/W2163588476","https://openalex.org/W4255475599","https://openalex.org/W2544674189","https://openalex.org/W2897171874"],"abstract_inverted_index":{"In":[0,34,49],"Web":[1,8,22,47,85],"environment,":[2],"in":[3,152,163],"order":[4],"to":[5,10,16,66,169],"provide":[6],"appropriate":[7],"services":[9],"users'":[11],"needs":[12],"it":[13],"becomes":[14],"important":[15],"quickly":[17],"and":[18,31,59,64,80,113,133,158],"accurately":[19],"extract":[20],"from":[21,46,56,98],"documents":[23],"contents":[24,45,156],"such":[25],"as":[26],"main-content,":[27],"menu-list,":[28],"article-list,":[29],"comments":[30],"so":[32],"on.":[33],"this":[35],"paper,":[36],"we":[37,90,138],"propose":[38],"an":[39],"efficient":[40],"method":[41,127,146],"that":[42,137,144],"extracts":[43],"various":[44],"documents.":[48],"the":[50,57,117,170],"method,":[51],"text":[52,72,111,119],"blocks":[53,112],"are":[54,121],"separated":[55],"document":[58],"context":[60],"information":[61,75],"is":[62,96],"extracted":[63],"used":[65],"classify":[67],"content":[68],"type":[69],"of":[70,77,83,116],"each":[71],"block.":[73],"Context":[74],"consists":[76],"documenting":[78,88],"patterns":[79],"structural":[81,107],"features":[82],"a":[84,103,129,134],"document.":[86],"For":[87,106],"patterns,":[89],"use":[91],"in/out":[92],"link":[93],"information,":[94],"which":[95],"expanded":[97],"word/link":[99],"density":[100],"proposed":[101],"by":[102],"previous":[104],"work.":[105],"features,":[108],"distances":[109],"between":[110],"parent":[114],"tags":[115],"target":[118],"block":[120],"used.":[122],"We":[123],"experimented":[124],"with":[125],"our":[126,145],"using":[128],"published":[130],"data":[131,135],"set":[132,136],"collected.":[139],"The":[140],"experiment":[141],"results":[142],"show":[143],"performs":[147],"about":[148,159],"17%":[149],"points":[150,161],"better":[151,162],"accuracy":[153],"for":[154,165],"multiple":[155],"extraction":[157,167],"14%":[160],"F-measure":[164],"main-content":[166],"compared":[168],"existing":[171],"methods.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}