{"id":"https://openalex.org/W2462693065","doi":"https://doi.org/10.1145/2911451.2914719","title":"Enhancing First Story Detection using Word Embeddings","display_name":"Enhancing First Story Detection using Word Embeddings","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2462693065","doi":"https://doi.org/10.1145/2911451.2914719","mag":"2462693065"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","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/A5035887312","display_name":"Se\u00e1n Moran","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sean Moran","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057657785","display_name":"Richard McCreadie","orcid":"https://orcid.org/0000-0002-2751-2087"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard McCreadie","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035887312"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":8.5694,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97667216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"821","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7082322835922241},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6405960917472839},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47350603342056274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39240413904190063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38821911811828613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15713077783584595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082322835922241},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6405960917472839},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47350603342056274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39240413904190063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38821911811828613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15713077783584595},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2911451.2914719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:119287","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/view/author/35492.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2756725110","display_name":"Urban Big Data","funder_award_id":"ES/L011921/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G2758810241","display_name":null,"funder_award_id":"ES/L011921/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G6924631477","display_name":null,"funder_award_id":"FP7-606853","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W174630521","https://openalex.org/W1500025080","https://openalex.org/W1614298861","https://openalex.org/W2012833704","https://openalex.org/W2081580037","https://openalex.org/W2105846817","https://openalex.org/W2108701407","https://openalex.org/W2140427797","https://openalex.org/W2147717514","https://openalex.org/W2250752175","https://openalex.org/W2950577311","https://openalex.org/W2964232225"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,55,85,104],"this":[1,56,86,95],"paper":[2],"we":[3,88,106,138],"show":[4,139],"how":[5],"word":[6,119],"embeddings":[7,120],"can":[8,143],"be":[9,61,144],"used":[10],"to":[11,47,93,108],"increase":[12],"the":[13,48],"effectiveness":[14,49,142],"of":[15,50,97,134],"a":[16,30,44,51,58,64,69,82,90,122,129,149],"state-of-the":[17],"art":[18],"Locality":[19],"Sensitive":[20],"Hashing":[21],"(LSH)":[22],"based":[23,100],"first":[24,65,83],"story":[25,66],"detection":[26],"(FSD)":[27],"system":[28],"over":[29,121,148],"standard":[31],"tweet":[32,59,102,124],"corpus.":[33,125],"Vocabulary":[34],"mismatch,":[35],"in":[36],"which":[37,72],"related":[38,70,113],"tweets":[39,110],"use":[40],"different":[41,74],"words,":[42,77],"is":[43],"serious":[45],"hindrance":[46],"modern":[52],"FSD":[53,141,151],"system.":[54,152],"case,":[57],"could":[60],"flagged":[62],"as":[63,81],"even":[67],"if":[68],"tweet,":[71],"uses":[73],"but":[75],"synonymous":[76],"was":[78],"already":[79],"returned":[80],"story.":[84],"work,":[87],"propose":[89,107],"novel":[91],"approach":[92],"mitigate":[94],"problem":[96],"lexical":[98],"variation,":[99],"on":[101,128],"expansion.":[103],"particular,":[105],"expand":[109],"with":[111],"semantically":[112],"paraphrases":[114],"identified":[115],"via":[116],"automatically":[117],"mined":[118],"background":[123],"Through":[126],"experimentation":[127],"large":[130],"data":[131],"stream":[132],"comprised":[133],"50":[135],"million":[136],"tweets,":[137],"that":[140],"improved":[145],"by":[146],"9.5%":[147],"state-of-the-art":[150]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}