{"id":"https://openalex.org/W1906699800","doi":"https://doi.org/10.1145/2488388.2488499","title":"Groundhog day","display_name":"Groundhog day","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W1906699800","doi":"https://doi.org/10.1145/2488388.2488499","mag":"1906699800"},"language":"en","primary_location":{"id":"doi:10.1145/2488388.2488499","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488388.2488499","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 international conference on World Wide Web","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/A5005065765","display_name":"Ke Tao","orcid":"https://orcid.org/0000-0002-8014-8587"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ke Tao","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands","Delft University of Technology, Delft, Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080218207","display_name":"Fabian Abel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Abel","raw_affiliation_strings":["XING AG, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"XING AG, Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084915697","display_name":"Claudia Hauff","orcid":"https://orcid.org/0000-0001-9879-6470"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Claudia Hauff","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands","Delft University of Technology, Delft, Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108504427","display_name":"Geert\u2010Jan Houben","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Geert-Jan Houben","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands","Delft University of Technology, Delft, Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038081564","display_name":"Ujwal Gadiraju","orcid":"https://orcid.org/0000-0002-6189-6539"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ujwal Gadiraju","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands","Delft University of Technology, Delft, Netherlands;"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands;","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005065765"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":16.9896,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98847555,"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":"1273","last_page":"1284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9994000196456909,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8532265424728394},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.7314304113388062},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6074498891830444},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5990428924560547},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5765997171401978},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5572580695152283},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.45830702781677246},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4494950473308563},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41114574670791626},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3625904619693756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19122058153152466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532265424728394},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.7314304113388062},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6074498891830444},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5990428924560547},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5765997171401978},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5572580695152283},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.45830702781677246},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4494950473308563},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41114574670791626},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3625904619693756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19122058153152466},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2488388.2488499","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488388.2488499","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 international conference on World Wide Web","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":28,"referenced_works":["https://openalex.org/W11244355","https://openalex.org/W184758014","https://openalex.org/W1583837637","https://openalex.org/W1647729745","https://openalex.org/W1972594216","https://openalex.org/W1993320088","https://openalex.org/W1995672491","https://openalex.org/W2012833704","https://openalex.org/W2019177758","https://openalex.org/W2066682493","https://openalex.org/W2070242009","https://openalex.org/W2081580037","https://openalex.org/W2085264282","https://openalex.org/W2085922539","https://openalex.org/W2101196063","https://openalex.org/W2104583100","https://openalex.org/W2107126505","https://openalex.org/W2122390506","https://openalex.org/W2124499489","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2152847636","https://openalex.org/W2181829939","https://openalex.org/W2238991082","https://openalex.org/W2406682228","https://openalex.org/W2482128004","https://openalex.org/W2912431181","https://openalex.org/W4239647775"],"related_works":["https://openalex.org/W2728430307","https://openalex.org/W2107786128","https://openalex.org/W2053241453","https://openalex.org/W2153980712","https://openalex.org/W2537388533","https://openalex.org/W2978974359","https://openalex.org/W2036556872","https://openalex.org/W2021183651","https://openalex.org/W2017590198","https://openalex.org/W2353191283"],"abstract_inverted_index":{"With":[0],"more":[1],"than":[2],"340~million":[3],"messages":[4],"that":[5,35,57,103,131,179,206],"are":[6,90,210],"posted":[7],"on":[8,41,51,170,201],"Twitter":[9,52,125,144],"every":[10],"day,":[11],"the":[12,20,46,59,141,155,165,175,195,217],"amount":[13],"of":[14,48,85,143,157,167,177,197,219],"duplicate":[15,24,77,106,111,171,199],"content":[16,40,200],"as":[17,19,190],"well":[18],"demand":[21],"for":[22,124,160],"appropriate":[23],"detection":[25,50,78,112],"mechanisms":[26],"is":[27,96],"increasing":[28],"tremendously.":[29],"Yet":[30],"there":[31],"exists":[32],"little":[33],"research":[34],"aims":[36],"at":[37],"detecting":[38,161,220],"near-duplicate":[39,49],"microblogging":[42],"platforms.":[43],"We":[44,108,146],"investigate":[45,174],"problem":[47],"and":[53,69,139,192],"introduce":[54],"a":[55,121],"framework":[56,74,113,214],"analyzes":[58],"tweets":[60],"by":[61,116,212],"comparing":[62],"(i)":[63],"syntactical":[64],"characteristics,":[65],"(ii)":[66],"semantic":[67,207],"similarity,":[68],"(iii)":[70],"contextual":[71],"information.":[72],"Our":[73,203],"provides":[75],"different":[76,158],"strategies":[79,159,178],"that,":[80],"among":[81],"others,":[82],"make":[83],"use":[84],"external":[86],"Web":[87],"resources":[88],"which":[89,151,209],"referenced":[91],"from":[92],"microposts.":[93],"Machine":[94],"learning":[95],"exploited":[97],"in":[98,150],"order":[99],"to":[100,135,181],"learn":[101],"patterns":[102],"help":[104],"identifying":[105,198],"content.":[107],"put":[109],"our":[110,213],"into":[114,119],"practice":[115],"integrating":[117],"it":[118,132],"Twinder,":[120],"search":[122,137],"engine":[123],"streams.":[126],"An":[127],"in-depth":[128],"analysis":[129],"shows":[130],"allows":[133],"Twinder":[134],"diversify":[136],"results":[138,204],"improve":[140],"quality":[142,156,176],"search.":[145],"conduct":[147],"extensive":[148],"experiments":[149],"we":[152],"(1)":[153],"evaluate":[154],"duplicates,":[162],"(2)":[163],"analyze":[164],"impact":[166],"various":[168],"features":[169,208],"detection,":[172],"(3)":[173],"classify":[180],"what":[182],"exact":[183],"level":[184],"two":[185],"microposts":[186],"can":[187,215],"be":[188],"considered":[189],"duplicates":[191],"(4)":[193],"optimize":[194],"process":[196],"Twitter.":[202],"prove":[205],"extracted":[211],"boost":[216],"performance":[218],"duplicates.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2016-06-24T00:00:00"}
