{"id":"https://openalex.org/W2811298255","doi":"https://doi.org/10.13053/cys-22-2-2959","title":"Improving the Boilerpipe Algorithm for Boilerplate Removal in News Articles Using HTML Tree Structure","display_name":"Improving the Boilerpipe Algorithm for Boilerplate Removal in News Articles Using HTML Tree Structure","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2811298255","doi":"https://doi.org/10.13053/cys-22-2-2959","mag":"2811298255"},"language":"en","primary_location":{"id":"doi:10.13053/cys-22-2-2959","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-2-2959","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-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/A5024411618","display_name":"Francisco Viveros-Jim\u00e9nez","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Francisco Viveros-Jim\u00e9nez","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066678199","display_name":"Miguel A. S\u00e1nchez-Pereza","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Miguel A. S\u00e1nchez-Pereza","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013558219","display_name":"Helena G\u00f3mez-Adorno","orcid":"https://orcid.org/0000-0002-6966-9912"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Helena G\u00f3mez-Adorno","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113477762","display_name":"Juan Pablo Posadas-Dur\u00e1n","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Juan Pablo Posadas-Dur\u00e1n","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Grigori Sidorov","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049701126","display_name":"Alexander Gelbukh","orcid":"https://orcid.org/0000-0001-7845-9039"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Alexander Gelbukh","raw_affiliation_strings":["INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO"],"affiliations":[{"raw_affiliation_string":"INSTITUTO POLIT\u00c9CNICO NACIONAL, MEXICO","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024411618"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":null,"apc_paid":null,"fwci":1.9635,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89896187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"22","issue":"2","first_page":null,"last_page":null},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.98089998960495,"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/T13976","display_name":"Web visibility and informetrics","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.8088301420211792},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7537481784820557},{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.6377929449081421},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.6164114475250244},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.48219385743141174},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48023444414138794},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44471031427383423},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4275309443473816},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3776417672634125},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25251004099845886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2376886010169983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088301420211792},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7537481784820557},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.6377929449081421},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.6164114475250244},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.48219385743141174},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48023444414138794},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44471031427383423},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4275309443473816},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3776417672634125},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25251004099845886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2376886010169983},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-22-2-2959","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-2-2959","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W1566513354","https://openalex.org/W2040075907"],"related_works":["https://openalex.org/W2999218465","https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W4288026874","https://openalex.org/W2989347554","https://openalex.org/W4302086745","https://openalex.org/W2373402338","https://openalex.org/W3010940303","https://openalex.org/W2114620981","https://openalex.org/W2626998250"],"abstract_inverted_index":{"It":[0],"is":[1,9,86,103,113,191],"well-known":[2],"that":[3,185],"the":[4,49,58,69,100,106,116,123,126,130,136,141,144,161,174,186],"lack":[5],"of":[6,33,57,72,77,105,115,125,135,181,188],"quality":[7],"data":[8,23],"a":[10,39,46,88],"major":[11],"problem":[12],"for":[13,95,133,143],"information":[14],"retrieval":[15],"engines.":[16],"Web":[17],"articles":[18],"are":[19,36,92],"flooded":[20],"with":[21,163],"non-relevant":[22],"such":[24],"as":[25],"advertising":[26],"and":[27,55,156,159],"related":[28],"links.":[29],"More":[30],"over,":[31],"some":[32],"these":[34],"ads":[35],"loaded":[37],"in":[38,80,99],"randomized":[40],"way":[41],"every":[42],"time":[43],"you":[44],"hit":[45],"page,":[47],"so":[48],"HTML":[50,131],"document":[51],"will":[52,60],"be":[53,61],"different":[54],"hashing":[56],"content":[59],"not":[62,87],"possible.":[63],"Therefore,":[64],"we":[65,121],"need":[66],"to":[67],"extract":[68],"relevant":[70,78,137,189],"text":[71,79,82,190],"documents.":[73],"The":[74],"automatic":[75],"extraction":[76],"on-line":[81],"(news":[83],"articles,":[84],"etc.)":[85],"trivial":[89],"task.":[90],"There":[91],"many":[93],"algorithms":[94],"this":[96,119],"purpose":[97],"described":[98],"literature.":[101],"Boilerpipe":[102,127],"one":[104,109,114],"most":[107],"popular":[108],"sand":[110],"its":[111],"performance":[112],"best.":[117],"In":[118],"paper,":[120],"improve":[122],"precision":[124],"algorithm":[128],"using":[129],"tree":[132],"selection":[134],"content.":[138],"We":[139,147,176],"make":[140],"experiments":[142],"news":[145,153],"articles.":[146],"evaluated":[148],"our":[149,182],"approach":[150,167],"by":[151],"extracting":[152],"from":[154,173],"English":[155],"Spanish":[157],"websites":[158],"compared":[160],"results":[162,170],"other":[164],"approaches.":[165],"Our":[166],"achieved":[168],"better":[169],"than":[171,193],"approaches":[172],"state-of-the-art.":[175],"also":[177],"present":[178],"an":[179],"analysis":[180],"dataset":[183],"confirming":[184],"amount":[187],"less":[192],"40%.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
