{"id":"https://openalex.org/W2160654919","doi":"https://doi.org/10.1145/2505515.2505695","title":"Building a large-scale corpus for evaluating event detection on twitter","display_name":"Building a large-scale corpus for evaluating event detection on twitter","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2160654919","doi":"https://doi.org/10.1145/2505515.2505695","mag":"2160654919"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information &amp; Knowledge Management","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/A5013830699","display_name":"Andrew James McMinn","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":false,"raw_author_name":"Andrew J. McMinn","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059100610","display_name":"Yashar Moshfeghi","orcid":"https://orcid.org/0000-0003-4186-1088"},"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":"Yashar Moshfeghi","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"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":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":11.9911,"has_fulltext":false,"cited_by_count":224,"citation_normalized_percentile":{"value":0.98934338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.8124593496322632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028339147567749},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7941630482673645},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6852161288261414},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6666474938392639},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6399630308151245},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6356804370880127},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6200528740882874},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5157251954078674},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48089027404785156},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4619441628456116},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4202682375907898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40512967109680176},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3793483078479767},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19023770093917847}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8124593496322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028339147567749},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7941630482673645},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6852161288261414},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6666474938392639},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6399630308151245},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6356804370880127},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6200528740882874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5157251954078674},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48089027404785156},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4619441628456116},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4202682375907898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40512967109680176},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3793483078479767},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19023770093917847},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2505515.2505695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:128478","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/128478/","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W9223698","https://openalex.org/W11244355","https://openalex.org/W112197792","https://openalex.org/W159497295","https://openalex.org/W1534625513","https://openalex.org/W1594112393","https://openalex.org/W1977931290","https://openalex.org/W1998224037","https://openalex.org/W2001653897","https://openalex.org/W2052635433","https://openalex.org/W2066682493","https://openalex.org/W2079054072","https://openalex.org/W2105846817","https://openalex.org/W2112377492","https://openalex.org/W2121911157","https://openalex.org/W2124499489","https://openalex.org/W2140427797","https://openalex.org/W2339562433","https://openalex.org/W2341079710","https://openalex.org/W2404243041","https://openalex.org/W6600459962","https://openalex.org/W6703967046","https://openalex.org/W6704412327"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W1497983610","https://openalex.org/W1980158193"],"abstract_inverted_index":{"Despite":[0],"the":[1,42,50,53,56,74,85,97,139,157,196,237],"popularity":[2],"of":[3,38,44,52,58,69,76,87,99,115,135,141,151,159,168,180,198,211,239],"Twitter":[4,45,217],"for":[5,25,73,96,128,236],"research,":[6],"there":[7],"are":[8,17,19],"very":[9],"few":[10],"publicly":[11],"available":[12,18,127],"corpora,":[13,46],"and":[14,55,118,143,174,194,205],"those":[15],"which":[16,124,137,232],"either":[20],"too":[21],"small":[22],"or":[23],"unsuitable":[24],"tasks":[26],"such":[27,63],"as":[28],"event":[29,77,101,136,160,171,240],"detection.":[30,161],"This":[31],"is":[32,79],"partially":[33],"due":[34],"to":[35,176,190],"a":[36,64,94,108,113,133,149,178,209],"number":[37],"issues":[39],"associated":[40,184],"with":[41,183,215],"creation":[43,98],"including":[47,200],"restrictions":[48],"on":[49],"distribution":[51],"tweets":[54],"difficultly":[57],"creating":[59,70],"relevance":[60,71,152,192,221],"judgements":[61,72,153,222],"at":[62,156],"large":[65],"scale.":[66],"The":[67],"difficulty":[68],"task":[75,158],"detection":[78,102,172,241],"further":[80],"hampered":[81],"by":[82],"ambiguity":[83],"in":[84],"definition":[86,134],"event.":[88],"In":[89],"this":[90,145,212],"paper,":[91],"we":[92,105,125,147,165,202,219],"propose":[93,132],"methodology":[95],"an":[100],"corpus.":[103],"Specifically,":[104],"first":[106],"create":[107],"new":[109],"corpus":[110],"that":[111],"covers":[112],"period":[114],"4":[116],"weeks":[117],"contains":[119],"over":[120,224],"120":[121],"million":[122],"tweets,":[123,226],"make":[126,166],"research.":[129],"We":[130,186],"then":[131,187],"fits":[138],"characteristics":[140],"Twitter,":[142],"using":[144],"definition,":[146],"generate":[148,177],"set":[150,179],"aimed":[154],"specifically":[155],"To":[162],"do":[163],"so,":[164],"use":[167,188],"existing":[169],"state-of-the-art":[170],"approaches":[173],"Wikipedia":[175],"candidate":[181],"events":[182],"tweets.":[185],"crowdsourcing":[189],"gather":[191],"judgements,":[193],"discuss":[195],"quality":[197],"results,":[199],"how":[201],"ensured":[203],"integrity":[204],"prevented":[206],"spam.":[207],"As":[208],"result":[210],"process,":[213],"along":[214],"our":[216],"corpus,":[218],"release":[220],"containing":[223],"150,000":[225],"covering":[227],"more":[228],"than":[229],"500":[230],"events,":[231],"can":[233],"be":[234],"used":[235],"evaluation":[238],"approaches.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":8}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
