{"id":"https://openalex.org/W7155061869","doi":"https://doi.org/10.1109/synasc69064.2025.00046","title":"CrossRead: An NLP Pipeline for Identifying Similar News Articles Across Multiple Sources","display_name":"CrossRead: An NLP Pipeline for Identifying Similar News Articles Across Multiple Sources","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7155061869","doi":"https://doi.org/10.1109/synasc69064.2025.00046"},"language":null,"primary_location":{"id":"doi:10.1109/synasc69064.2025.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/synasc69064.2025.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 27th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5134124482","display_name":"Victor-Miron Boiangiu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Victor-Miron Boiangiu","raw_affiliation_strings":["National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073856277","display_name":"\u015etefan Ru\u015fe\u0163i","orcid":"https://orcid.org/0000-0002-0380-6814"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Stefan Ruseti","raw_affiliation_strings":["National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134182580","display_name":"Mihai Dascalu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mihai Dascalu","raw_affiliation_strings":["National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology, POLITEHNICA Bucharest,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.14300000667572021,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.14300000667572021,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.13429999351501465,"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/T10028","display_name":"Topic Modeling","score":0.07289999723434448,"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/pipeline","display_name":"Pipeline (software)","score":0.7055000066757202},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.31279999017715454},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26010000705718994},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2143000066280365}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6198999881744385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5795999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685999989509583},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21870000660419464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21660000085830688},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2143000066280365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/synasc69064.2025.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/synasc69064.2025.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 27th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2791544114","https://openalex.org/W2980708516","https://openalex.org/W3093031973","https://openalex.org/W4385571011","https://openalex.org/W4414485088"],"related_works":[],"abstract_inverted_index":{"The":[0,66,161],"rate":[1],"at":[2],"which":[3],"fake":[4,34],"news":[5,35,49,131],"articles":[6,41,153,158],"are":[7],"written":[8],"and":[9,24,60,83,150],"disseminated":[10],"on":[11,51],"social":[12],"media":[13],"is":[14,71],"alarming,":[15],"posing":[16],"a":[17,52,72,118,170],"significant":[18],"threat":[19],"to":[20,39,45,146,178],"both":[21],"national":[22],"security":[23],"individual":[25],"well-being.":[26],"This":[27],"paper":[28],"supports":[29],"mitigating":[30],"the":[31,64,69,78,85,91,94,122,186],"propagation":[32],"of":[33,68,112,125,128,130],"by":[36,42],"empowering":[37],"individuals":[38],"fact-check":[40,152],"comparing":[43],"them":[44,56],"those":[46],"from":[47],"trustworthy":[48],"organizations":[50],"platform":[53,163],"that":[54,76],"helps":[55],"find":[57],"alternative":[58,81],"sources":[59,149],"identify":[61],"discrepancies":[62],"between":[63],"articles.":[65],"backbone":[67],"solution":[70],"3-staged":[73],"processing":[74],"pipeline":[75],"processes":[77],"article,":[79,120],"fetches":[80],"sources,":[82],"generates":[84],"final":[86],"similarity":[87],"report.":[88],"For":[89],"fine-tuning":[90],"models":[92],"in":[93,159,182],"pipeline,":[95,141],"two":[96],"new":[97],"corpora":[98],"were":[99,105],"created,":[100],"as":[101,134],"no":[102],"existing":[103],"datasets":[104],"available":[106],"for":[107,117,169,185],"Romanian.":[108,160],"One":[109],"corpus":[110],"consisted":[111,124],"synthetically":[113],"generated":[114],"search":[115,184],"queries":[116],"given":[119],"whereas":[121],"second":[123],"human":[126],"annotations":[127],"pairs":[129],"articles,":[132],"labeled":[133],"either":[135],"similar":[136],"or":[137],"not":[138],"similar.":[139],"Our":[140],"named":[142],"CrossRead,":[143],"enables":[144],"users":[145,181],"easily":[147],"compare":[148],"quickly":[151],"while":[154],"working":[155],"reliably":[156],"with":[157,174],"presented":[162],"also":[164],"constitutes":[165],"an":[166],"excellent":[167],"base":[168],"more":[171],"feature-rich":[172],"solution,":[173],"numerous":[175],"improvements":[176],"possible":[177],"assist":[179],"its":[180],"their":[183],"truth.":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-22T00:00:00"}