{"id":"https://openalex.org/W84052264","doi":"https://doi.org/10.5220/0003665304700475","title":"EXTRACTING THE MAIN CONTENT OF WEB DOCUMENTS BASED ON A NAIVE SMOOTHING METHOD","display_name":"EXTRACTING THE MAIN CONTENT OF WEB DOCUMENTS BASED ON A NAIVE SMOOTHING METHOD","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W84052264","doi":"https://doi.org/10.5220/0003665304700475","mag":"84052264"},"language":"en","primary_location":{"id":"doi:10.5220/0003665304700475","doi":"https://doi.org/10.5220/0003665304700475","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0003665304700475","pdf_url":null,"source":{"id":"https://openalex.org/S4306419631","display_name":"International Conference on Knowledge Discovery and Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0003665304700475","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089589635","display_name":"Hadi Mohammadzadeh","orcid":"https://orcid.org/0009-0009-9021-5825","observed_orcids":["https://orcid.org/0009-0009-9021-5825"]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hadi Mohammadzadeh","raw_affiliation_strings":["Universit\u00e4t Ulm, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Ulm, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007509091","display_name":"Thomas Gottron","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Gottron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087969414","display_name":"Franz Schweiggert","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franz Schweiggert","raw_affiliation_strings":["Universit\u00e4t Ulm, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Ulm, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112428141","display_name":"Gholamreza Nakhaeizadeh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gholamreza Nakhaeizadeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4177,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.52359209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"475"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":9.999999747378752e-05,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/main-content-extraction","display_name":"main content extraction","score":0.9909999966621399},{"id":"https://openalex.org/keywords/web-pages","display_name":"web pages","score":0.7139999866485596},{"id":"https://openalex.org/keywords/html-parsing","display_name":"HTML parsing","score":0.7310000061988831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119674921035767},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6106564402580261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.501812219619751},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.49259406328201294},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4840959310531616},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3985518217086792},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2719278633594513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06997191905975342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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:10.5220/0003665304700475","doi":"https://doi.org/10.5220/0003665304700475","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0003665304700475","pdf_url":null,"source":{"id":"https://openalex.org/S4306419631","display_name":"International Conference on Knowledge Discovery and Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0003665304700475","doi":"https://doi.org/10.5220/0003665304700475","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0003665304700475","pdf_url":null,"source":{"id":"https://openalex.org/S4306419631","display_name":"International Conference on Knowledge Discovery and Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W100562005","https://openalex.org/W116870935","https://openalex.org/W1566513354","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2019577381","https://openalex.org/W2063147917","https://openalex.org/W2117209866","https://openalex.org/W2117694587","https://openalex.org/W2130186082","https://openalex.org/W2147220393","https://openalex.org/W2147466442","https://openalex.org/W2162744351","https://openalex.org/W2171502989","https://openalex.org/W2520948221"],"related_works":["https://openalex.org/W2520948221","https://openalex.org/W4285704047","https://openalex.org/W2897171874","https://openalex.org/W2091855574","https://openalex.org/W3130845557","https://openalex.org/W2328581567","https://openalex.org/W3174829772","https://openalex.org/W7097483186","https://openalex.org/W2184048696","https://openalex.org/W2233365824"],"abstract_inverted_index":{"Extracting":[0],"the":[1,18,31,70,75,98,101,113,116,126,138,142],"main":[2,32,45,102,117,128,139],"content":[3,33,46,78,118,129,140],"of":[4,34,54,61,77,81,115,141],"web":[5,35,144],"documents,":[6],"with":[7,43],"high":[8,50],"accuracy,":[9],"is":[10,64],"an":[11,85,120],"important":[12],"challenge":[13],"for":[14,29],"researchers":[15],"working":[16],"on":[17],"web.":[19],"In":[20,69],"this":[21],"paper,":[22],"we":[23,73,106,124],"present":[24],"a":[25,92,108],"novel":[26],"language-independent":[27],"method":[28,95],"extracting":[30],"pages.":[36],"Our":[37],"method,":[38],"called":[39],"DANAg,":[40],"in":[41,52,84,119,134],"comparison":[42],"other":[44],"extraction":[47,59],"approaches":[48],"has":[49],"performance":[51],"terms":[53],"effectiveness":[55],"and":[56,79],"efficiency.":[57],"The":[58,88],"process":[60],"data":[62],"DANAg":[63],"divided":[65],"into":[66],"four":[67],"phases.":[68],"first":[71],"phase,":[72],"calculate":[74],"length":[76],"code":[80],"fixed":[82],"segments":[83,99],"HTML":[86,121],"file.":[87,122],"second":[89],"phase":[90],"applies":[91],"naive":[93],"smoothing":[94],"to":[96,111,131,136],"highlight":[97],"forming":[100],"content.":[103],"After":[104],"that,":[105],"use":[107],"simple":[109],"algorithm":[110],"recognize":[112],"boundary":[114],"Finally,":[123],"feed":[125],"selected":[127],"area":[130],"our":[132],"parser":[133],"order":[135],"extract":[137],"targeted":[143],"page.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}