{"id":"https://openalex.org/W2739642838","doi":"https://doi.org/10.1145/3090354.3090419","title":"Syntactic entropy for main content extraction from web pages","display_name":"Syntactic entropy for main content extraction from web pages","publication_year":2017,"publication_date":"2017-03-29","ids":{"openalex":"https://openalex.org/W2739642838","doi":"https://doi.org/10.1145/3090354.3090419","mag":"2739642838"},"language":"en","primary_location":{"id":"doi:10.1145/3090354.3090419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3090354.3090419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international Conference on Big Data, Cloud and Applications","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/A5063354884","display_name":"Ismail Jellouli","orcid":"https://orcid.org/0009-0004-4153-2406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ismail Jellouli","raw_affiliation_strings":["Computer Science Department, Tetuan, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Tetuan, Morocco","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112242640","display_name":"Badr Eddine El Mohajir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Badr Eddine El Mohajir","raw_affiliation_strings":["Computer Science Department, Tetuan, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Tetuan, Morocco","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110532723","display_name":"Mohammed Al Achhab","orcid":"https://orcid.org/0000-0003-4669-0564"},"institutions":[{"id":"https://openalex.org/I4210093720","display_name":"National School of Architecture","ror":"https://ror.org/00n7n3773","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210093720"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mohammed Al Achhab","raw_affiliation_strings":["The National Applied Science School, Tetuan, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The National Applied Science School, Tetuan, Morocco","institution_ids":["https://openalex.org/I4210093720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12925017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9674999713897705,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9273999929428101,"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":0.8482807874679565},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8002874851226807},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5704247951507568},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5117008686065674},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4840675890445709},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4836619794368744},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43721917271614075},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.43669500946998596},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4189406633377075},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33102554082870483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10929298400878906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482807874679565},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8002874851226807},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5704247951507568},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5117008686065674},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4840675890445709},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4836619794368744},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43721917271614075},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.43669500946998596},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4189406633377075},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33102554082870483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10929298400878906},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3090354.3090419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3090354.3090419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international Conference on Big Data, Cloud and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W1968053850","https://openalex.org/W2019577381","https://openalex.org/W2051141368","https://openalex.org/W2076665947","https://openalex.org/W2120101509","https://openalex.org/W2140208587","https://openalex.org/W2158051716","https://openalex.org/W2167859982","https://openalex.org/W2201534957"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W36911888","https://openalex.org/W2083329789","https://openalex.org/W2376574812","https://openalex.org/W4385731361"],"abstract_inverted_index":{"In":[0],"this":[1,83],"paper,":[2],"we":[3],"present":[4],"a":[5],"solution":[6,15,46,84],"for":[7],"main":[8],"content":[9,64],"identification":[10],"in":[11,23],"web":[12,52,89],"pages.":[13],"Our":[14],"is":[16,27,34,38,43],"language-independent;":[17],"Web":[18],"pages":[19,53,90],"may":[20],"be":[21],"written":[22],"different":[24],"languages.":[25],"It":[26],"topic-independent;":[28],"no":[29,40],"domain":[30],"knowledge":[31],"or":[32],"dictionary":[33],"applied.":[35],"And":[36],"it":[37,97],"unsupervised;":[39],"training":[41],"phase":[42],"necessary.":[44],"The":[45,99],"exploits":[47],"the":[48,55,67,70,74,77],"tree":[49],"structure":[50],"of":[51,57,63,69,88],"and":[54,72,95],"frequencies":[56],"text":[58],"tokens":[59],"to":[60,66,91],"attribute":[61],"scores":[62],"density":[65],"areas":[68],"page":[71],"by":[73],"way":[75],"identify":[76],"most":[78],"important":[79],"one.":[80],"We":[81],"tested":[82],"over":[85],"representative":[86],"examples":[87],"show":[92],"how":[93],"efficient":[94],"accurate":[96],"is.":[98],"results":[100],"were":[101],"satisfying.":[102]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
