{"id":"https://openalex.org/W6944289077","doi":"https://doi.org/10.18452/1447","title":"news-please","display_name":"news-please","publication_year":2017,"publication_date":"2017-03-24","ids":{"openalex":"https://openalex.org/W6944289077","doi":"https://doi.org/10.18452/1447"},"language":"en","primary_location":{"id":"pmh:oai:edoc.hu-berlin.de:18452/2099","is_oa":true,"landing_page_url":"http://edoc.hu-berlin.de/18452/2099","pdf_url":"http://edoc.hu-berlin.de/18452/2099","source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://edoc.hu-berlin.de/18452/2099","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hamborg, Felix","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hamborg, Felix","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Meuschke, Norman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meuschke, Norman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Breitinger, Corinna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Breitinger, Corinna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gipp, Bela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gipp, Bela","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.33651467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13568","display_name":"Wood and Agarwood Research","score":0.04089999943971634,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13568","display_name":"Wood and Agarwood Research","score":0.04089999943971634,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13238","display_name":"Botanical Studies and Applications","score":0.03759999945759773,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7307000160217285},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7139999866485596},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6536999940872192},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4672999978065491},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.45320001244544983},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/information-resource","display_name":"Information resource","score":0.36980000138282776}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7307000160217285},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7139999866485596},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6536999940872192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151000261306763},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.597000002861023},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C3017942907","wikidata":"https://www.wikidata.org/wiki/Q16797616","display_name":"Information resource","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.26660001277923584}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:edoc.hu-berlin.de:18452/2099","is_oa":true,"landing_page_url":"http://edoc.hu-berlin.de/18452/2099","pdf_url":"http://edoc.hu-berlin.de/18452/2099","source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/106756","is_oa":false,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/106756","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"no"},{"id":"doi:10.18452/1447","is_oa":true,"landing_page_url":"https://doi.org/10.18452/1447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:edoc.hu-berlin.de:18452/2099","is_oa":true,"landing_page_url":"http://edoc.hu-berlin.de/18452/2099","pdf_url":"http://edoc.hu-berlin.de/18452/2099","source":{"id":"https://openalex.org/S4306400923","display_name":"edoc Publication server (Humboldt University of Berlin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39343248","host_organization_name":"Humboldt-Universit\u00e4t zu Berlin","host_organization_lineage":["https://openalex.org/I39343248"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"sustainable_development_goals":[{"score":0.4943365156650543,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6944289077.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"amount":[1],"of":[2,35,44,72,87],"news":[3,15,36,64,73,80,88],"published":[4],"and":[5,29,49,61,82,102],"read":[6],"online":[7],"has":[8],"increased":[9],"tremendously":[10],"in":[11],"recent":[12],"years,":[13],"making":[14],"data":[16,37],"an":[17],"interesting":[18],"resource":[19],"for":[20,47,63,68],"many":[21],"research":[22],"disciplines,":[23],"such":[24,51],"as":[25],"the":[26,84,116],"social":[27],"sciences":[28],"linguistics.":[30],"However,":[31],"large":[32,70],"scale":[33],"collection":[34],"is":[38],"cumbersome":[39],"due":[40],"to":[41,106],"a":[42,56,69],"lack":[43],"generic":[45],"tools":[46],"crawling":[48,78],"extracting":[50,83],"data.":[52],"We":[53],"present":[54],"news-please,":[55],"generic,":[57],"multilanguage,":[58],"open-source":[59],"crawler":[60],"extractor":[62],"that":[65],"works":[66],"out-of-the-box":[67],"variety":[71],"websites.":[74],"Our":[75],"system":[76],"allows":[77],"arbitrary":[79],"websites":[81],"major":[85],"elements":[86],"articles":[89],"on":[90],"those":[91],"websites,":[92],"i.e.,":[93],"title,":[94],"lead":[95],"paragraph,":[96],"main":[97,103],"content,":[98],"publication":[99],"date,":[100],"author,":[101],"image.":[104],"Compared":[105],"existing":[107],"tools,":[108],"news-please":[109],"features":[110],"full":[111],"website":[112],"extraction":[113],"requiring":[114],"only":[115],"root":[117],"URL.":[118]},"counts_by_year":[],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}