{"id":"https://openalex.org/W4318147649","doi":"https://doi.org/10.1109/bigdata55660.2022.10020983","title":"Twitter Bot Detection Through Unsupervised Machine Learning","display_name":"Twitter Bot Detection Through Unsupervised Machine Learning","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318147649","doi":"https://doi.org/10.1109/bigdata55660.2022.10020983"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020983","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5102479826","display_name":"Jeremy Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I149530613","display_name":"Lynn University","ror":"https://ror.org/04nqv0v23","country_code":"US","type":"education","lineage":["https://openalex.org/I149530613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Wu","raw_affiliation_strings":["Lynbrook High School,San Jose,United States of America","Lynbrook High School, San Jose, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lynbrook High School,San Jose,United States of America","institution_ids":["https://openalex.org/I149530613"]},{"raw_affiliation_string":"Lynbrook High School, San Jose, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028443853","display_name":"Eric Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I881441977","display_name":"Los Angeles Mission College","ror":"https://ror.org/01stcbz02","country_code":"US","type":"education","lineage":["https://openalex.org/I2802998804","https://openalex.org/I881441977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Teng","raw_affiliation_strings":["Mission San Jose High School,Fremont,United States of America","Mission San Jose High School, Fremont, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mission San Jose High School,Fremont,United States of America","institution_ids":["https://openalex.org/I881441977"]},{"raw_affiliation_string":"Mission San Jose High School, Fremont, United States of America","institution_ids":["https://openalex.org/I881441977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102584968","display_name":"Ziyue Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123080","display_name":"Green Valley High School","ror":"https://ror.org/033cjdk78","country_code":"US","type":"education","lineage":["https://openalex.org/I4210123080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyue Cao","raw_affiliation_strings":["Amador Valley High School,Pleasanton,United States of America","Amador Valley High School, Pleasanton, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amador Valley High School,Pleasanton,United States of America","institution_ids":["https://openalex.org/I4210123080"]},{"raw_affiliation_string":"Amador Valley High School, Pleasanton, United States of America","institution_ids":["https://openalex.org/I4210123080"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7277,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73991993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5833","last_page":"5839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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":1.0,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9980999827384949,"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/python","display_name":"Python (programming language)","score":0.8320947885513306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888862490653992},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7546401023864746},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.7321000099182129},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5750530362129211},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5626064538955688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5597145557403564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384421944618225},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5070018768310547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3499550223350525},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27340972423553467}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8320947885513306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888862490653992},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7546401023864746},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.7321000099182129},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5750530362129211},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5626064538955688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5597145557403564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384421944618225},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5070018768310547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3499550223350525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27340972423553467},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020983","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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":16,"referenced_works":["https://openalex.org/W2028475679","https://openalex.org/W2101234009","https://openalex.org/W2535218596","https://openalex.org/W2583516892","https://openalex.org/W2752154653","https://openalex.org/W2893495107","https://openalex.org/W2944790037","https://openalex.org/W2953721269","https://openalex.org/W2997788455","https://openalex.org/W3018700748","https://openalex.org/W3102083609","https://openalex.org/W4393145327","https://openalex.org/W6630590103","https://openalex.org/W6755321125","https://openalex.org/W6765518407","https://openalex.org/W6770204077"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W4294565801","https://openalex.org/W2142306706"],"abstract_inverted_index":{"Identification":[0],"a":[1,51,90,124,160,164,167],"nd":[2],"r":[3],"emoval":[4],"o":[5],"f":[6,7,53],"ake":[8],"internet":[9,15],"accounts":[10,74,133,141],"have":[11,69],"become":[12],"crucial":[13],"for":[14,21],"safety.":[16],"Much":[17],"of":[18,42,93,126],"existing":[19],"research":[20,86],"bot":[22,44,130,165],"detection":[23],"uses":[24],"supervised":[25],"machine":[26],"learning,":[27],"in":[28,159],"addition":[29],"to":[30,38,88,142],"detecting":[31,57,80],"URL":[32],"usage":[33],"and":[34,46,79,97,104,115,131,138],"sentiment":[35],"analysis.":[36],"Due":[37],"the":[39,47,111,119,135],"limited":[40],"availability":[41],"labeled":[43],"data":[45,117],"difficulties":[48],"s":[49],"upervised":[50],"lgorithms":[52],"ace":[54],"i":[55],"n":[56],"adaptive":[58],"behavior,":[59],"an":[60,157],"unsupervised":[61],"approach":[62],"would":[63],"be":[64],"more":[65],"appropriate.":[66],"Past":[67],"studies":[68],"attempted":[70],"this":[71],"by":[72],"clustering":[73,99],"based":[75,152],"on":[76,153],"post":[77],"activity":[78],"spam":[81],"through":[82,95],"embedded":[83],"URLs.":[84],"Our":[85],"attempts":[87],"detect":[89],"broader":[91],"range":[92],"bots":[94],"K-Means":[96],"Agglomerative":[98],"using":[100,110],"account":[101,158],"activity,":[102],"popularity,":[103],"Twitter":[105,120],"verification,":[106],"among":[107],"others.":[108],"After":[109],"Scikit-learn":[112],"Python":[113],"library":[114],"collecting":[116],"from":[118,134],"API,":[121],"we":[122],"used":[123],"dataset":[125],"around":[127],"2,000":[128],"known":[129],"human":[132],"Bot":[136],"Repository":[137],"11,000":[139],"unlabelled":[140],"create":[143],"four":[144],"distinct":[145],"clusters.":[146],"We":[147],"then":[148],"measured":[149],"our":[150,154],"results":[151],"confidence":[155],"that":[156],"particular":[161],"cluster":[162],"was":[163],"or":[166],"human.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}