{"id":"https://openalex.org/W2602442722","doi":"https://doi.org/10.1109/kst.2017.7886134","title":"SVM-based web content mining with leaf classification unit from DOM-tree","display_name":"SVM-based web content mining with leaf classification unit from DOM-tree","publication_year":2017,"publication_date":"2017-02-01","ids":{"openalex":"https://openalex.org/W2602442722","doi":"https://doi.org/10.1109/kst.2017.7886134","mag":"2602442722"},"language":"en","primary_location":{"id":"doi:10.1109/kst.2017.7886134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst.2017.7886134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 9th International Conference on Knowledge and Smart Technology (KST)","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/A5012918458","display_name":"Yeong-Su Kim","orcid":"https://orcid.org/0000-0002-9831-2883"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeongsu Kim","raw_affiliation_strings":["Dept. of Big Data Science, Korea Institute of Science and Technology Information (KISTI), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Big Data Science, Korea Institute of Science and Technology Information (KISTI), Daejeon, Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403754","display_name":"Seungwoo Lee","orcid":"https://orcid.org/0000-0002-2987-150X"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungwoo Lee","raw_affiliation_strings":["Dept. of Big Data Science, Korea Institute of Science and Technology Information (KISTI), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Big Data Science, Korea Institute of Science and Technology Information (KISTI), Daejeon, Korea","institution_ids":["https://openalex.org/I878022262"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012918458"],"corresponding_institution_ids":["https://openalex.org/I878022262"],"apc_list":null,"apc_paid":null,"fwci":0.9673,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81279716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"359","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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":0.9975000023841858,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9855999946594238,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9789000153541565,"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":0.8083272576332092},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.7513085007667542},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6076092720031738},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.60457444190979},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5880184173583984},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5754319429397583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5007340908050537},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49140703678131104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4428303837776184},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4307112693786621},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42468202114105225},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34484153985977173},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18916872143745422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07483553886413574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083272576332092},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7513085007667542},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6076092720031738},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.60457444190979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5880184173583984},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5754319429397583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007340908050537},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49140703678131104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4428303837776184},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4307112693786621},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42468202114105225},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34484153985977173},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18916872143745422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07483553886413574},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kst.2017.7886134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst.2017.7886134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 9th International Conference on Knowledge and Smart Technology (KST)","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":15,"referenced_works":["https://openalex.org/W34519199","https://openalex.org/W100562005","https://openalex.org/W156734151","https://openalex.org/W1587356454","https://openalex.org/W1986598368","https://openalex.org/W2007442002","https://openalex.org/W2008056655","https://openalex.org/W2012575882","https://openalex.org/W2031517079","https://openalex.org/W2126226592","https://openalex.org/W2163588476","https://openalex.org/W4254066415","https://openalex.org/W6604096230","https://openalex.org/W6606309775","https://openalex.org/W6635377069"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W4200355488","https://openalex.org/W127000293","https://openalex.org/W3215892509","https://openalex.org/W2928616779","https://openalex.org/W2412592434","https://openalex.org/W2010523086","https://openalex.org/W4244602709","https://openalex.org/W594987446","https://openalex.org/W1985727224"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,51,58,73,92],"analyze":[3],"a":[4,71,85,97,119,123,161],"news":[5,46,59,80],"article":[6],"dataset,":[7],"we":[8,26,104,117],"first":[9],"extract":[10],"important":[11,69],"information":[12,29,108],"such":[13,30],"as":[14,31,122,146],"title,":[15],"date,":[16],"and":[17,37,53,61],"paragraph":[18],"of":[19,45,64,79,152,155],"the":[20,23,43,110,128,143,153],"body.":[21],"At":[22],"same":[24],"time,":[25],"remove":[27,137],"unnecessary":[28],"image,":[32],"caption,":[33],"footer,":[34],"advertisement,":[35],"navigation":[36],"recommended-news.":[38],"The":[39],"problem":[40],"is":[41,68,90],"that":[42,84,106],"formats":[44,78],"articles":[47],"are":[48],"changing":[49],"according":[50,57],"time":[52],"also":[54],"they":[55,141,158],"vary":[56],"source":[60],"even":[62],"section":[63],"it.":[65],"So,":[66],"it":[67],"for":[70],"model":[72,89,99],"generalize":[74],"when":[75],"predicting":[76],"unseen":[77],"articles.":[81],"We":[82],"confirmed":[83],"machine":[86,132],"learning":[87,133],"based":[88,134],"better":[91],"predict":[93],"new":[94],"data":[95],"than":[96],"rule-based":[98],"by":[100],"some":[101],"experiments.":[102],"Also,":[103],"suggest":[105],"noise":[107,138],"in":[109],"body":[111],"possibly":[112],"can":[113],"be":[114],"removed":[115],"because":[116],"define":[118],"classification":[120,144],"unit":[121,145],"leaf":[124,156,162],"node":[125,149,163],"itself.":[126,164],"On":[127],"other":[129],"hand,":[130],"general":[131],"models":[135],"cannot":[136,159],"information.":[139],"Since":[140],"consider":[142],"an":[147],"intermediate":[148],"which":[150],"consists":[151],"set":[154],"nodes,":[157],"classify":[160]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}