{"id":"https://openalex.org/W4396534802","doi":"https://doi.org/10.46298/jdmdh.13123","title":"Towards efficient and reliable utilization of automated data collection: Media scrapers applied to news on climate change","display_name":"Towards efficient and reliable utilization of automated data collection: Media scrapers applied to news on climate change","publication_year":2024,"publication_date":"2024-04-29","ids":{"openalex":"https://openalex.org/W4396534802","doi":"https://doi.org/10.46298/jdmdh.13123"},"language":"en","primary_location":{"id":"doi:10.46298/jdmdh.13123","doi":"https://doi.org/10.46298/jdmdh.13123","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.13123","pdf_url":"https://jdmdh.episciences.org/13426/pdf","source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jdmdh.episciences.org/13426/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027312233","display_name":"Erkki Mervaala","orcid":"https://orcid.org/0000-0002-0144-7010","observed_orcids":["https://orcid.org/0000-0002-0144-7010"]},"institutions":[{"id":"https://openalex.org/I2800424308","display_name":"Finnish Environment Institute","ror":"https://ror.org/013nat269","country_code":"FI","type":"government","lineage":["https://openalex.org/I2800424308","https://openalex.org/I4210136438"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Erkki Mervaala","raw_affiliation_strings":["Finnish Environment Institute","Finnish Environment Institute Syke, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0144-7010","affiliations":[{"raw_affiliation_string":"Finnish Environment Institute","institution_ids":["https://openalex.org/I2800424308"]},{"raw_affiliation_string":"Finnish Environment Institute Syke, Finland","institution_ids":["https://openalex.org/I2800424308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088486359","display_name":"Jari M. Lyytim\u00e4ki","orcid":"https://orcid.org/0000-0003-3308-5234","observed_orcids":["https://orcid.org/0000-0003-3308-5234"]},"institutions":[{"id":"https://openalex.org/I2800424308","display_name":"Finnish Environment Institute","ror":"https://ror.org/013nat269","country_code":"FI","type":"government","lineage":["https://openalex.org/I2800424308","https://openalex.org/I4210136438"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jari Lyytim\u00e4ki","raw_affiliation_strings":["Finnish Environment Institute","Finnish Environment Institute Syke, Finland"],"raw_orcid":"https://orcid.org/0000-0003-3308-5234","affiliations":[{"raw_affiliation_string":"Finnish Environment Institute","institution_ids":["https://openalex.org/I2800424308"]},{"raw_affiliation_string":"Finnish Environment Institute Syke, Finland","institution_ids":["https://openalex.org/I2800424308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027312233"],"corresponding_institution_ids":["https://openalex.org/I2800424308"],"apc_list":null,"apc_paid":null,"fwci":0.8748,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84816176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"NLP4DH","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.7588000297546387,"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":0.7588000297546387,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.23180000483989716,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automated-data-collection","display_name":"automated data collection","score":0.847000002861023},{"id":"https://openalex.org/keywords/climate-change-news","display_name":"climate change news","score":0.7170000076293945},{"id":"https://openalex.org/keywords/media-coverage","display_name":"media coverage","score":0.9700000286102295},{"id":"https://openalex.org/keywords/finland","display_name":"Finland","score":0.7009999752044678},{"id":"https://openalex.org/keywords/data-completeness","display_name":"data completeness","score":0.3659999966621399},{"id":"https://openalex.org/keywords/systematic-errors","display_name":"systematic errors","score":0.5609999895095825},{"id":"https://openalex.org/keywords/manual-control","display_name":"manual control","score":0.3479999899864197},{"id":"https://openalex.org/keywords/digital-archives","display_name":"digital archives","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C78500136","wikidata":"https://www.wikidata.org/wiki/Q477840","display_name":"Scraper site","level":2,"score":0.5261251926422119},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5245847105979919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49604472517967224},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.435351699590683},{"id":"https://openalex.org/C132651083","wikidata":"https://www.wikidata.org/wiki/Q7942","display_name":"Climate change","level":2,"score":0.41988813877105713},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2533937990665436},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2447361946105957},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.17617663741111755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14997723698616028},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11305224895477295}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.46298/jdmdh.13123","doi":"https://doi.org/10.46298/jdmdh.13123","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.13123","pdf_url":"https://jdmdh.episciences.org/13426/pdf","source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:721a9ca3425648ca92d2f8cc35b178d9","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/721a9ca3425648ca92d2f8cc35b178d9","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Data Mining and Digital Humanities, Vol NLP4DH (2024)","raw_type":"article"},{"id":"pmh:oai:helda.helsinki.fi:10138/585678","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/585678","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:helda.helsinki.fi:10138/590344","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/590344","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"A1 Alkuper\u00e4isartikkeli tieteellisess\u00e4 aikakauslehdess\u00e4"},{"id":"doi:10.5281/zenodo.10715204","doi":"https://doi.org/10.5281/zenodo.10715204","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10715204","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.10715205","doi":"https://doi.org/10.5281/zenodo.10715205","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10715205","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.46298/jdmdh.13123","doi":"https://doi.org/10.46298/jdmdh.13123","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.13123","pdf_url":"https://jdmdh.episciences.org/13426/pdf","source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.685699999332428}],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.8199999928474426}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396534802.pdf","grobid_xml":"https://content.openalex.org/works/W4396534802.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1977200906","https://openalex.org/W1986771330","https://openalex.org/W1988574456","https://openalex.org/W1993576492","https://openalex.org/W2026608375","https://openalex.org/W2074275669","https://openalex.org/W2170650244","https://openalex.org/W2194828565","https://openalex.org/W2267527226","https://openalex.org/W2433203947","https://openalex.org/W2571102916","https://openalex.org/W2897674311","https://openalex.org/W2916191585","https://openalex.org/W2949480888","https://openalex.org/W2956617434","https://openalex.org/W2982587173","https://openalex.org/W3024177297","https://openalex.org/W3025627210","https://openalex.org/W3081573265","https://openalex.org/W3092908287","https://openalex.org/W3111842105","https://openalex.org/W3125851220","https://openalex.org/W3211631450","https://openalex.org/W4200146754","https://openalex.org/W4200258507","https://openalex.org/W4383912341"],"related_works":["https://openalex.org/W2897674311","https://openalex.org/W6982168398","https://openalex.org/W7052489940","https://openalex.org/W7216169040","https://openalex.org/W3006970579","https://openalex.org/W7111804498","https://openalex.org/W4398822247","https://openalex.org/W4393728011","https://openalex.org/W3165669050","https://openalex.org/W2988143608"],"abstract_inverted_index":{"Abstract:":[0],"Automated":[1],"data":[2,14,47,83,100],"collection":[3,48],"provides":[4],"tempting":[5],"opportunities":[6],"for":[7,131],"social":[8],"sciences":[9],"and":[10,24,29,45,49,52,60,123,141],"humanities":[11],"studies.":[12],"Abundant":[13],"accumulating":[15],"in":[16,72,107],"various":[17],"digital":[18],"archives":[19],"allows":[20],"more":[21],"comprehensive,":[22],"timely":[23],"cost-efficient":[25],"ways":[26],"of":[27,38,58,79,81,86,104,134,144],"harvesting":[28],"processing":[30],"information.":[31,92],"While":[32],"easing":[33],"or":[34,84,90],"even":[35],"removing":[36],"some":[37],"the":[39,82],"key":[40],"problems,":[41],"such":[42,75,116],"as":[43,76,117],"laborious":[44],"time-consuming":[46],"potential":[50],"errors":[51,89],"biases":[53],"related":[54],"to":[55,98],"subjective":[56],"coding":[57],"materials":[59],"distortions":[61],"caused":[62],"by":[63],"focus":[64],"on":[65,113,147],"small":[66],"samples,":[67],"automated":[68],"methods":[69,97],"also":[70],"bring":[71],"new":[73],"risks":[74],"poor":[77],"understanding":[78],"contexts":[80],"non-recognition":[85],"underlying":[87],"systematic":[88],"missing":[91],"Results":[93],"from":[94],"testing":[95],"different":[96],"collect":[99],"describing":[101],"newspaper":[102],"coverage":[103],"climate":[105],"change":[106],"Finland":[108],"emphasize":[109],"that":[110],"fully":[111],"relying":[112],"automatable":[114],"tools":[115],"media":[118],"scrapers":[119],"has":[120],"its":[121],"limitations":[122,136],"can":[124],"provide":[125],"comprehensive":[126],"but":[127],"incomplete":[128],"document":[129],"acquisition":[130],"research.":[132],"Many":[133],"these":[135],"can,":[137],"however,":[138],"be":[139],"addressed":[140],"not":[142],"all":[143],"them":[145],"rely":[146],"manual":[148],"control.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-11T09:32:39.932853","created_date":"2024-05-01T00:00:00"}
