{"id":"https://openalex.org/W4415815752","doi":"https://doi.org/10.3390/data10110174","title":"Web Scraping Chilean News Media: A Dataset for Analyzing Social Unrest Coverage (2019\u20132023)","display_name":"Web Scraping Chilean News Media: A Dataset for Analyzing Social Unrest Coverage (2019\u20132023)","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415815752","doi":"https://doi.org/10.3390/data10110174"},"language":"en","primary_location":{"id":"doi:10.3390/data10110174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10110174","pdf_url":"https://www.mdpi.com/2306-5729/10/11/174/pdf?version=1762152358","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/10/11/174/pdf?version=1762152358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058607088","display_name":"Ignacio Molina","orcid":"https://orcid.org/0009-0003-0535-5521"},"institutions":[{"id":"https://openalex.org/I2802166871","display_name":"Universidad Cat\u00f3lica del Norte","ror":"https://ror.org/02akpm128","country_code":"CL","type":"education","lineage":["https://openalex.org/I2802166871"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Ignacio Molina","raw_affiliation_strings":["Department of Systems and Computing Engineering, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile"],"raw_orcid":"https://orcid.org/0009-0003-0535-5521","affiliations":[{"raw_affiliation_string":"Department of Systems and Computing Engineering, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile","institution_ids":["https://openalex.org/I2802166871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109572195","display_name":"Jos\u00e9 Manuel Robles Morales","orcid":"https://orcid.org/0009-0006-3850-840X"},"institutions":[{"id":"https://openalex.org/I2802166871","display_name":"Universidad Cat\u00f3lica del Norte","ror":"https://ror.org/02akpm128","country_code":"CL","type":"education","lineage":["https://openalex.org/I2802166871"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Morales","raw_affiliation_strings":["School of Journalism, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile"],"raw_orcid":"https://orcid.org/0009-0006-3850-840X","affiliations":[{"raw_affiliation_string":"School of Journalism, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile","institution_ids":["https://openalex.org/I2802166871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073250946","display_name":"Brian Keith","orcid":"https://orcid.org/0000-0001-5734-8962"},"institutions":[{"id":"https://openalex.org/I2802166871","display_name":"Universidad Cat\u00f3lica del Norte","ror":"https://ror.org/02akpm128","country_code":"CL","type":"education","lineage":["https://openalex.org/I2802166871"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Brian Keith","raw_affiliation_strings":["Department of Systems and Computing Engineering, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile"],"raw_orcid":"https://orcid.org/0000-0001-5734-8962","affiliations":[{"raw_affiliation_string":"Department of Systems and Computing Engineering, Universidad Cat\u00f3lica del Norte, Antofagasta 1270398, Chile","institution_ids":["https://openalex.org/I2802166871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073250946"],"corresponding_institution_ids":["https://openalex.org/I2802166871"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":3.8911,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95580759,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"10","issue":"11","first_page":"174","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.23749999701976776,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.23749999701976776,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.16380000114440918,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.13359999656677246,"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/social-media","display_name":"Social media","score":0.6496000289916992},{"id":"https://openalex.org/keywords/unrest","display_name":"Unrest","score":0.5102999806404114},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4986000061035156},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.4609000086784363},{"id":"https://openalex.org/keywords/social-unrest","display_name":"Social unrest","score":0.4341000020503998},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.3953000009059906},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C2778358470","wikidata":"https://www.wikidata.org/wiki/Q7897387","display_name":"Unrest","level":3,"score":0.5102999806404114},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C2994499861","wikidata":"https://www.wikidata.org/wiki/Q686984","display_name":"Social unrest","level":3,"score":0.4341000020503998},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.36739999055862427},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3553999960422516},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.337799996137619},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C529147693","wikidata":"https://www.wikidata.org/wiki/Q1193236","display_name":"News media","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2632000148296356}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/data10110174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10110174","pdf_url":"https://www.mdpi.com/2306-5729/10/11/174/pdf?version=1762152358","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2172597af27743a49bcc3d4ac19282b1","is_oa":true,"landing_page_url":"https://doaj.org/article/2172597af27743a49bcc3d4ac19282b1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 10, Iss 11, p 174 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/data10110174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data10110174","pdf_url":"https://www.mdpi.com/2306-5729/10/11/174/pdf?version=1762152358","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415815752.pdf","grobid_xml":"https://content.openalex.org/works/W4415815752.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1529013893","https://openalex.org/W1563091572","https://openalex.org/W1920240025","https://openalex.org/W2076583243","https://openalex.org/W2080481858","https://openalex.org/W2302501749","https://openalex.org/W2788315304","https://openalex.org/W2791544114","https://openalex.org/W2797202416","https://openalex.org/W2914472818","https://openalex.org/W2916741972","https://openalex.org/W2949992436","https://openalex.org/W2979620102","https://openalex.org/W3034824379","https://openalex.org/W3046459713","https://openalex.org/W3120436057","https://openalex.org/W3134218298","https://openalex.org/W3167108461","https://openalex.org/W3196972353","https://openalex.org/W3202318235","https://openalex.org/W3211928360","https://openalex.org/W3215663352","https://openalex.org/W3217346043","https://openalex.org/W3217767782","https://openalex.org/W4205508543","https://openalex.org/W4210827551","https://openalex.org/W4213426538","https://openalex.org/W4214933429","https://openalex.org/W4244170802","https://openalex.org/W4306732251","https://openalex.org/W4315490272","https://openalex.org/W4318055116","https://openalex.org/W4322766946","https://openalex.org/W4366453415","https://openalex.org/W4366986851","https://openalex.org/W4385284981","https://openalex.org/W4386479634","https://openalex.org/W4387498736","https://openalex.org/W4389880954","https://openalex.org/W4390700333","https://openalex.org/W4392172801","https://openalex.org/W4402667000","https://openalex.org/W4403540049","https://openalex.org/W4404466235","https://openalex.org/W4405214092","https://openalex.org/W4406909578","https://openalex.org/W4406910435","https://openalex.org/W4409773258","https://openalex.org/W4410638118","https://openalex.org/W4412087931"],"related_works":[],"abstract_inverted_index":{"This":[0,111],"paper":[1],"presents":[2],"a":[3],"dataset":[4,94,129],"of":[5,48],"Chilean":[6,34,68],"news":[7,35,72],"media":[8,116],"coverage":[9,117],"during":[10,118],"the":[11,67],"social":[12,69],"unrest":[13],"and":[14,27,41,63,108,121,130],"constitutional":[15],"processes":[16],"from":[17,32],"2019":[18,40],"to":[19,53,66,79,88],"2023.":[20,44],"Using":[21],"Python-based":[22],"web":[23],"scraping":[24],"with":[25,83,100],"BeautifulSoup":[26],"Selenium,":[28],"we":[29],"collected":[30],"articles":[31,50,64],"15":[33,38],"outlets":[36,85],"between":[37],"November":[39],"17":[42],"December":[43],"The":[45,93,128],"initial":[46],"collection":[47],"1254":[49],"was":[51],"filtered":[52],"931":[54],"usable":[55],"data":[56,123],"points":[57],"after":[58],"removing":[59],"non-relevant":[60],"content,":[61,105],"duplicates,":[62],"unrelated":[65],"outburst.":[70],"Each":[71],"outlet":[73],"required":[74],"specific":[75],"extraction":[76,131],"approaches":[77],"due":[78,87],"varying":[80],"HTML":[81],"structures,":[82],"some":[84],"inaccessible":[86],"paywalls":[89],"or":[90],"anti-scraping":[91],"mechanisms.":[92],"is":[95],"structured":[96],"in":[97],"JSON":[98],"format":[99],"standardized":[101],"fields":[102],"including":[103],"title,":[104],"date,":[106],"author,":[107],"source":[109],"metadata.":[110],"resource":[112],"supports":[113],"research":[114],"on":[115,136],"political":[119],"events":[120],"provides":[122],"for":[124],"Spanish-language":[125],"processing":[126],"tasks.":[127],"code":[132],"are":[133],"publicly":[134],"available":[135],"GitHub.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-11-03T00:00:00"}
