{"id":"https://openalex.org/W3122771337","doi":"https://doi.org/10.1145/3428757.3429104","title":"Web Scraping versus Twitter API","display_name":"Web Scraping versus Twitter API","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3122771337","doi":"https://doi.org/10.1145/3428757.3429104","mag":"3122771337"},"language":"en","primary_location":{"id":"doi:10.1145/3428757.3429104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/20.500.12390/2460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073133852","display_name":"Irvin Dongo","orcid":"https://orcid.org/0000-0003-4859-0428"},"institutions":[{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210089347","display_name":"\u00c9cole Sup\u00e9rieure des Technologies Industrielles Avanc\u00e9es","ror":"https://ror.org/008kvxw43","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210089347"]},{"id":"https://openalex.org/I4210134504","display_name":"Universidad Cat\u00f3lica San Pablo","ror":"https://ror.org/03db1hz44","country_code":"PE","type":"education","lineage":["https://openalex.org/I4210134504"]}],"countries":["FR","PE"],"is_corresponding":false,"raw_author_name":"Irvin Dongo","raw_affiliation_strings":["Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa, Univ. Bordeaux, ESTIA INSTITUTE OF TECHNOLOGY, Bidart, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa, Univ. Bordeaux, ESTIA INSTITUTE OF TECHNOLOGY, Bidart, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210089347","https://openalex.org/I4210134504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018552300","display_name":"Yudith Cadinale","orcid":null},"institutions":[{"id":"https://openalex.org/I629287","display_name":"Sim\u00f3n Bol\u00edvar University","ror":"https://ror.org/01ak5cj98","country_code":"VE","type":"education","lineage":["https://openalex.org/I629287"]}],"countries":["VE"],"is_corresponding":false,"raw_author_name":"Yudith Cadinale","raw_affiliation_strings":["Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa, Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Cat\u00f3lica San Pablo, Arequipa, Per\u00fa, Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela","institution_ids":["https://openalex.org/I629287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060109964","display_name":"Ana Aguilera","orcid":"https://orcid.org/0000-0003-0726-1759"},"institutions":[{"id":"https://openalex.org/I79274474","display_name":"University of Valpara\u00edso","ror":"https://ror.org/00h9jrb69","country_code":"CL","type":"education","lineage":["https://openalex.org/I79274474"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Ana Aguilera","raw_affiliation_strings":["Escuela de Ingenier\u00eda Inform\u00e1tica, Universidad de Valpara\u00edso, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escuela de Ingenier\u00eda Inform\u00e1tica, Universidad de Valpara\u00edso, Chile","institution_ids":["https://openalex.org/I79274474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027777531","display_name":"Fabiola Mart\u00ednez","orcid":null},"institutions":[{"id":"https://openalex.org/I629287","display_name":"Sim\u00f3n Bol\u00edvar University","ror":"https://ror.org/01ak5cj98","country_code":"VE","type":"education","lineage":["https://openalex.org/I629287"]}],"countries":["VE"],"is_corresponding":false,"raw_author_name":"Fabiola Mart\u00ednez","raw_affiliation_strings":["Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela","institution_ids":["https://openalex.org/I629287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077118865","display_name":"Yuni Quintero","orcid":null},"institutions":[{"id":"https://openalex.org/I629287","display_name":"Sim\u00f3n Bol\u00edvar University","ror":"https://ror.org/01ak5cj98","country_code":"VE","type":"education","lineage":["https://openalex.org/I629287"]}],"countries":["VE"],"is_corresponding":false,"raw_author_name":"Yuni Quintero","raw_affiliation_strings":["Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Sim\u00f3n Bol\u00edvar, Caracas, Venezuela","institution_ids":["https://openalex.org/I629287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072556693","display_name":"Sergio Barrios","orcid":null},"institutions":[{"id":"https://openalex.org/I629287","display_name":"Sim\u00f3n Bol\u00edvar University","ror":"https://ror.org/01ak5cj98","country_code":"VE","type":"education","lineage":["https://openalex.org/I629287"]}],"countries":["VE"],"is_corresponding":false,"raw_author_name":"Sergio Barrios","raw_affiliation_strings":["Universidad Sim\u00f3n Bol\u00edvar Caracas, Venezuela"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Sim\u00f3n Bol\u00edvar Caracas, Venezuela","institution_ids":["https://openalex.org/I629287"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7897,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97050056,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.995199978351593,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9908999800682068,"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/credibility","display_name":"Credibility","score":0.8635843992233276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8089582920074463},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5980011224746704},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5739692449569702},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5051460862159729},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.46700653433799744},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4304667115211487},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39718466997146606}],"concepts":[{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.8635843992233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089582920074463},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5980011224746704},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5739692449569702},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5051460862159729},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.46700653433799744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4304667115211487},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39718466997146606},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3428757.3429104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03217665v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03217665","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"iiWAS '20: The 22nd International Conference on Information Integration and Web-based Applications & Services, Nov 2020, Chiang Mai, Thailand. pp.263-273, ⟨10.1145/3428757.3429104⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/172962","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/172962","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I15057530","host_organization_name":"Universit\u00e9 de Bordeaux","host_organization_lineage":["https://openalex.org/I15057530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication dans un congr\u00e8s"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/31907","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/31907","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I15057530","host_organization_name":"Universit\u00e9 de Bordeaux","host_organization_lineage":["https://openalex.org/I15057530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication dans un congr\u00e8s avec actes"},{"id":"pmh:oai:repositorio.concytec.gob.pe:20.500.12390/2460","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.12390/2460","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:CONCYTEC","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:repositorio.concytec.gob.pe:20.500.12390/2460","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.12390/2460","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:CONCYTEC","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1482969897","https://openalex.org/W1965558549","https://openalex.org/W1965859459","https://openalex.org/W2051405935","https://openalex.org/W2084591134","https://openalex.org/W2123354009","https://openalex.org/W2257105692","https://openalex.org/W2296706733","https://openalex.org/W2509979611","https://openalex.org/W2552253519","https://openalex.org/W2792307011","https://openalex.org/W2792709517","https://openalex.org/W2898441677","https://openalex.org/W2901492958","https://openalex.org/W2903782735","https://openalex.org/W2912453995","https://openalex.org/W2918166202","https://openalex.org/W2921351946","https://openalex.org/W2940716695","https://openalex.org/W2947431746","https://openalex.org/W2963523292","https://openalex.org/W3006352228","https://openalex.org/W3029824235","https://openalex.org/W3104758113","https://openalex.org/W3105189474","https://openalex.org/W3123437755","https://openalex.org/W4288281505"],"related_works":["https://openalex.org/W2388687352","https://openalex.org/W1990162851","https://openalex.org/W2370187191","https://openalex.org/W2369854048","https://openalex.org/W2374291020","https://openalex.org/W2355907197","https://openalex.org/W3171042291","https://openalex.org/W2390961115","https://openalex.org/W2388138913","https://openalex.org/W4396769302"],"abstract_inverted_index":{"Twitter":[0,31,162],"is":[1,118,145,159,166,177],"one":[2],"of":[3,23,88,106,171],"the":[4,11,21,24,38,71,86,89,93,148,154],"most":[5],"popular":[6],"information":[7,79],"source":[8],"available":[9],"on":[10,19,92],"Web.":[12,94],"Thus,":[13],"there":[14],"exist":[15],"many":[16],"studies":[17],"focused":[18],"analyzing":[20],"credibility":[22,87,114,138],"shared":[25],"information.":[26],"Most":[27],"proposals":[28],"use":[29],"either":[30],"API":[32],"or":[33],"web":[34,157,175],"scraping":[35,158,176],"to":[36,40,58,73,76,82,126,147,180],"extract":[37,77],"data":[39,107],"perform":[41],"such":[42],"analysis.":[43],"Both":[44],"extraction":[45,108],"techniques":[46],"have":[47],"advantages":[48],"and":[49,62,109,164],"disadvantages.":[50],"In":[51],"this":[52,67],"work,":[53],"we":[54,98],"present":[55],"a":[56,100,111,121,141],"study":[57],"evaluate":[59],"their":[60],"performance":[61],"behavior.":[63],"The":[64],"motivation":[65],"for":[66],"research":[68],"comes":[69],"from":[70],"necessity":[72],"know":[74],"ways":[75],"online":[78],"in":[80,84,129,169],"order":[81],"analyze":[83,127],"real-time":[85],"content":[90],"posted":[91],"To":[95],"do":[96],"so,":[97],"develop":[99],"framework":[101,117],"which":[102],"offers":[103],"both":[104,134],"alternatives":[105],"implements":[110],"previously":[112],"proposed":[113],"model.":[115],"Our":[116],"implemented":[119],"as":[120],"Google":[122],"Chrome":[123],"extension":[124],"able":[125],"tweets":[128],"real-time.":[130],"Results":[131],"report":[132],"that":[133],"methods":[135],"produce":[136],"identical":[137],"values,":[139],"when":[140],"robust":[142],"normalization":[143],"process":[144],"applied":[146],"text":[149],"(i.e.,":[150],"tweet).":[151],"Moreover,":[152],"concerning":[153],"time":[155],"performance,":[156],"faster":[160],"than":[161],"API,":[163],"it":[165],"more":[167],"flexible":[168],"terms":[170],"obtaining":[172],"data;":[173],"however,":[174],"very":[178],"sensitive":[179],"website":[181],"changes.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}