{"id":"https://openalex.org/W3011989059","doi":"https://doi.org/10.1145/3334480.3375225","title":"News Provenance: Revealing News Text Reuse at Web-Scale in an Augmented News Search Experience","display_name":"News Provenance: Revealing News Text Reuse at Web-Scale in an Augmented News Search Experience","publication_year":2020,"publication_date":"2020-04-25","ids":{"openalex":"https://openalex.org/W3011989059","doi":"https://doi.org/10.1145/3334480.3375225","mag":"3011989059"},"language":"en","primary_location":{"id":"doi:10.1145/3334480.3375225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3334480.3375225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems","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/A5103280164","display_name":"Nathan J. Evans","orcid":"https://orcid.org/0000-0002-6953-8816"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathan Evans","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018084938","display_name":"Darren Edge","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Darren Edge","raw_affiliation_strings":["Microsoft Research, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056572216","display_name":"Jonathan Larson","orcid":"https://orcid.org/0000-0002-8865-9306"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Larson","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067262667","display_name":"Christopher White","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher White","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103280164"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.0463,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84169272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9991000294685364,"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":0.9991000294685364,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9948999881744385,"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/transparency","display_name":"Transparency (behavior)","score":0.6732126474380493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6471055150032043},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.6323220729827881},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.6322429180145264},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5886595845222473},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.521621823310852},{"id":"https://openalex.org/keywords/news-media","display_name":"News media","score":0.5120823383331299},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4637610912322998},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.37936583161354065},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3558711111545563},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.27624720335006714},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.16662269830703735},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12419083714485168},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10976415872573853}],"concepts":[{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6732126474380493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471055150032043},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.6323220729827881},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.6322429180145264},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5886595845222473},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.521621823310852},{"id":"https://openalex.org/C529147693","wikidata":"https://www.wikidata.org/wiki/Q1193236","display_name":"News media","level":2,"score":0.5120823383331299},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4637610912322998},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.37936583161354065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3558711111545563},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.27624720335006714},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.16662269830703735},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12419083714485168},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10976415872573853},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3334480.3375225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3334480.3375225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W32013328","https://openalex.org/W128638292","https://openalex.org/W1967043694","https://openalex.org/W1983704604","https://openalex.org/W2126602876","https://openalex.org/W2142943833","https://openalex.org/W2148578434","https://openalex.org/W2164498220","https://openalex.org/W2320581117","https://openalex.org/W2510302779","https://openalex.org/W2582561810","https://openalex.org/W2789935117","https://openalex.org/W2795612851","https://openalex.org/W2795673640","https://openalex.org/W2906646536"],"related_works":["https://openalex.org/W4236382845","https://openalex.org/W4388712630","https://openalex.org/W2481168998","https://openalex.org/W2476994687","https://openalex.org/W642988558","https://openalex.org/W2324507472","https://openalex.org/W2511141457","https://openalex.org/W1999899047","https://openalex.org/W2173353921","https://openalex.org/W2354627941"],"abstract_inverted_index":{"The":[0],"media":[1,117],"industry":[2],"has":[3],"a":[4,13,23],"practice":[5],"of":[6,25,49,60,66,78,122],"reusing":[7],"news":[8,16,34,43,51,79],"content,":[9],"which":[10,92,97],"may":[11,83],"be":[12,84],"surprise":[14],"to":[15,31,86,94,99],"consumers.":[17],"Whether":[18],"by":[19,45],"agreement":[20],"or":[21],"plagiarism,":[22],"lack":[24],"explicit":[26],"citations":[27],"makes":[28],"it":[29,39,75],"difficult":[30],"understand":[32],"where":[33],"comes":[35],"from":[36],"and":[37,63,73,96,106,119],"how":[38],"spreads.":[40],"We":[41,101],"reveal":[42],"provenance":[44,71],"reconstructing":[46],"the":[47,53,58,64,110,114,120],"history":[48],"near-duplicate":[50],"in":[52],"web":[54],"index":[55],"-":[56],"identifying":[57],"origins":[59],"republished":[61],"content":[62],"impact":[65],"original":[67],"content.":[68],"By":[69],"aggregating":[70],"information":[72],"presenting":[74],"as":[76],"part":[77],"search":[80],"results,":[81],"users":[82],"able":[85],"make":[87],"more":[88],"informed":[89],"decisions":[90],"about":[91],"articles":[93],"read":[95],"publishers":[98],"trust.":[100],"report":[102],"on":[103],"early":[104],"analysis":[105],"user":[107],"feedback,":[108],"highlighting":[109],"critical":[111],"tension":[112],"between":[113],"desire":[115],"for":[116],"transparency":[118],"risks":[121],"disrupting":[123],"an":[124],"already":[125],"fragile":[126],"ecosystem.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}