{"id":"https://openalex.org/W2962482976","doi":"https://doi.org/10.1145/3341161.3342892","title":"Neural language model based training data augmentation for weakly supervised early rumor detection","display_name":"Neural language model based training data augmentation for weakly supervised early rumor detection","publication_year":2019,"publication_date":"2019-08-27","ids":{"openalex":"https://openalex.org/W2962482976","doi":"https://doi.org/10.1145/3341161.3342892","mag":"2962482976"},"language":"en","primary_location":{"id":"doi:10.1145/3341161.3342892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341161.3342892","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341161.3342892","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3341161.3342892","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sooji Han","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sooji Han","raw_affiliation_strings":["The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Gao","raw_affiliation_strings":["The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fabio Ciravegna","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fabio Ciravegna","raw_affiliation_strings":["The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.6495,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91877709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9765999913215637,"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/rumor","display_name":"Rumor","score":0.9581999778747559},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5982000231742859},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5084999799728394},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48660001158714294},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48489999771118164},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4406999945640564}],"concepts":[{"id":"https://openalex.org/C2780469804","wikidata":"https://www.wikidata.org/wiki/Q878352","display_name":"Rumor","level":2,"score":0.9581999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6110000014305115},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.26840001344680786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3341161.3342892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341161.3342892","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341161.3342892","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.07033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.07033","pdf_url":"https://arxiv.org/pdf/1907.07033","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3341161.3342892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341161.3342892","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341161.3342892","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962482976.pdf","grobid_xml":"https://content.openalex.org/works/W2962482976.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W621249151","https://openalex.org/W1832693441","https://openalex.org/W1990474689","https://openalex.org/W2125017820","https://openalex.org/W2153702313","https://openalex.org/W2170240176","https://openalex.org/W2289587777","https://openalex.org/W2293165966","https://openalex.org/W2466018483","https://openalex.org/W2540896251","https://openalex.org/W2558531213","https://openalex.org/W2577716227","https://openalex.org/W2577888896","https://openalex.org/W2606418518","https://openalex.org/W2609512471","https://openalex.org/W2736480860","https://openalex.org/W2737907513","https://openalex.org/W2757014168","https://openalex.org/W2758048150","https://openalex.org/W2798787718","https://openalex.org/W2803502351","https://openalex.org/W2803751389","https://openalex.org/W2808681756","https://openalex.org/W2893877992","https://openalex.org/W2946423414","https://openalex.org/W6676840489","https://openalex.org/W6748634344","https://openalex.org/W7074633423"],"related_works":[],"abstract_inverted_index":{"The":[0,37,126],"scarcity":[1],"and":[2,20,71,76,85,145,174,182],"class":[3,175],"imbalance":[4,176],"of":[5,96,120,123,136,196,206],"training":[6,214],"data":[7,22,46,140,170,181,215],"are":[8,90,110],"known":[9],"issues":[10],"in":[11,112,204],"current":[12],"rumor":[13,30,55,63,69,97,108,139,164,197,220],"detection":[14,31,165,198,221],"tasks.":[15],"We":[16],"propose":[17],"a":[18,117,160],"straight-forward":[19],"general-purpose":[21],"augmentation":[23],"technique":[24],"which":[25],"is":[26,40,60],"beneficial":[27],"to":[28,41,51,92,115,185,218],"early":[29],"relying":[32],"on":[33,48,62,104,223],"event":[34,45],"propagation":[35],"patterns.":[36],"key":[38],"idea":[39],"exploit":[42],"massive":[43],"unlabeled":[44,77],"sets":[47],"social":[49,147],"media":[50],"augment":[52],"limited":[53,179],"labeled":[54,75],"source":[56],"tweets.":[57,98],"This":[58],"work":[59],"based":[61,103],"spreading":[64],"patterns":[65],"revealed":[66],"by":[67,143,152,178,202],"recent":[68],"studies":[70],"semantic":[72],"relatedness":[73],"between":[74],"data.":[78],"A":[79],"state-of-the-art":[80,161],"neural":[81,188],"language":[82],"model":[83,166],"(NLM)":[84],"large":[86],"credibility-focused":[87],"Twitter":[88],"corpora":[89],"employed":[91,111],"learn":[93],"context-sensitive":[94],"representations":[95],"Six":[99],"different":[100],"real-world":[101],"events":[102],"three":[105],"publicly":[106],"available":[107],"datasets":[109],"our":[113,130],"experiments":[114,158,209],"provide":[116],"comparative":[118],"evaluation":[119],"the":[121,124,134,194],"effectiveness":[122],"method.":[125],"results":[127],"show":[128,167],"that":[129,168,212],"method":[131],"can":[132,171,183,199,216],"expand":[133],"size":[135],"an":[137],"existing":[138],"set":[141],"nearly":[142],"200%":[144],"corresponding":[146],"context":[148],"(i.e.,":[149],"conversational":[150],"threads)":[151],"100%":[153],"with":[154,159],"reasonable":[155],"quality.":[156],"Preliminary":[157],"deep":[162],"learning-based":[163],"augmented":[169,192,213],"alleviate":[172],"over-fitting":[173],"caused":[177],"train":[180,186],"help":[184,217],"complex":[187],"networks":[189],"(NNs).":[190],"With":[191],"data,":[193],"performance":[195],"be":[200],"improved":[201],"12.1%":[203],"terms":[205],"F-score.":[207],"Our":[208],"also":[210],"indicate":[211],"generalize":[219],"models":[222],"unseen":[224],"rumors.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2019-07-23T00:00:00"}