{"id":"https://openalex.org/W4367047167","doi":"https://doi.org/10.1145/3543507.3583214","title":"Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection","display_name":"Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367047167","doi":"https://doi.org/10.1145/3543507.3583214"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583214","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583214","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583214","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583214","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071310175","display_name":"Chris Hays","orcid":"https://orcid.org/0000-0002-3524-5564"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Hays","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085368888","display_name":"Zachary Schutzman","orcid":"https://orcid.org/0000-0002-3448-5654"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Schutzman","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052541789","display_name":"Manish Raghavan","orcid":"https://orcid.org/0000-0002-4155-8145"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Raghavan","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075790566","display_name":"Erin Walk","orcid":"https://orcid.org/0000-0002-8305-3161"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erin Walk","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040437487","display_name":"Philipp Zimmer","orcid":"https://orcid.org/0000-0002-5249-5151"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philipp Zimmer","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071310175"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":10.4191,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.98197318,"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":"3660","last_page":"3669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8373662233352661},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6681862473487854},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.5725383758544922},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5532363653182983},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47946465015411377},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.47048643231391907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44080162048339844},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.41122424602508545},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38145941495895386},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1941404640674591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373662233352661},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6681862473487854},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.5725383758544922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5532363653182983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47946465015411377},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.47048643231391907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44080162048339844},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.41122424602508545},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38145941495895386},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1941404640674591},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543507.3583214","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583214","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583214","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583214","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583214","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583214","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367047167.pdf","grobid_xml":"https://content.openalex.org/works/W4367047167.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W235909202","https://openalex.org/W1849719402","https://openalex.org/W1998871422","https://openalex.org/W2072715695","https://openalex.org/W2269924745","https://openalex.org/W2282821441","https://openalex.org/W2550819555","https://openalex.org/W2596225776","https://openalex.org/W2618851150","https://openalex.org/W2753241397","https://openalex.org/W2769056027","https://openalex.org/W2769471736","https://openalex.org/W2783638956","https://openalex.org/W2784117065","https://openalex.org/W2787037992","https://openalex.org/W2787296320","https://openalex.org/W2790166049","https://openalex.org/W2790757032","https://openalex.org/W2804365752","https://openalex.org/W2810193935","https://openalex.org/W2888571776","https://openalex.org/W2892724803","https://openalex.org/W2900641696","https://openalex.org/W2900936184","https://openalex.org/W2907352650","https://openalex.org/W2914084490","https://openalex.org/W2945976633","https://openalex.org/W2962862931","https://openalex.org/W2963806301","https://openalex.org/W2997788455","https://openalex.org/W2999021003","https://openalex.org/W2999115128","https://openalex.org/W3004034277","https://openalex.org/W3014935876","https://openalex.org/W3031781733","https://openalex.org/W3032981809","https://openalex.org/W3035082952","https://openalex.org/W3041367927","https://openalex.org/W3042328364","https://openalex.org/W3092091320","https://openalex.org/W3093798014","https://openalex.org/W3094505995","https://openalex.org/W3102083609","https://openalex.org/W3102114392","https://openalex.org/W3103318202","https://openalex.org/W3106311261","https://openalex.org/W3110578481","https://openalex.org/W3116492894","https://openalex.org/W3124726575","https://openalex.org/W3125928061","https://openalex.org/W3139427994","https://openalex.org/W3161393424","https://openalex.org/W3172230539","https://openalex.org/W3173253285","https://openalex.org/W3175498457","https://openalex.org/W3176405886","https://openalex.org/W3194561115","https://openalex.org/W3197022418","https://openalex.org/W3206289691","https://openalex.org/W3212368439","https://openalex.org/W4200222034","https://openalex.org/W4213147383","https://openalex.org/W4281631069","https://openalex.org/W4289253852","https://openalex.org/W4291366411","https://openalex.org/W4312579173","https://openalex.org/W4312680890","https://openalex.org/W6903254655"],"related_works":["https://openalex.org/W2317823609","https://openalex.org/W4241263575","https://openalex.org/W3130462184","https://openalex.org/W2902287117","https://openalex.org/W4318256508","https://openalex.org/W2401463593","https://openalex.org/W2349808627","https://openalex.org/W2391671934","https://openalex.org/W3023500690","https://openalex.org/W3124280623"],"abstract_inverted_index":{"Accurate":[0],"bot":[1,59,77,146,203],"detection":[2,78,147,204],"is":[3,14,79,94,103],"necessary":[4],"for":[5,17,71,84,188,206],"the":[6,20,26,53,96,116],"safety":[7],"and":[8,30,46,66,82,98,110,144,172,181,193,196],"integrity":[9],"of":[10,22,28,115,134],"online":[11],"platforms.":[12],"It":[13],"also":[15],"crucial":[16],"research":[18,200],"on":[19,57,73,130,140,168],"influence":[21],"bots":[23,180],"in":[24,86,107,191,199],"elections,":[25],"spread":[27],"misinformation,":[29],"financial":[31],"market":[32],"manipulation.":[33],"Platforms":[34],"deploy":[35],"infrastructure":[36],"to":[37,105,157],"flag":[38],"or":[39],"remove":[40],"automated":[41],"accounts,":[42],"but":[43],"their":[44],"tools":[45,62,205],"data":[47],"are":[48,165],"not":[49,95,154],"publicly":[50],"available.":[51],"Thus,":[52],"public":[54],"must":[55],"rely":[56],"third-party":[58],"detection.":[60],"These":[61,183],"employ":[63],"machine":[64],"learning":[65],"often":[67],"achieve":[68,137],"near-perfect":[69],"performance":[70,102,139],"classification":[72],"existing":[74,202],"datasets,":[75,148],"suggesting":[76],"accurate,":[80],"reliable":[81],"fit":[83],"use":[85],"downstream":[87],"applications.":[88],"We":[89],"provide":[90],"evidence":[91],"that":[92,100,121,145,163],"this":[93],"case":[97],"show":[99,120],"high":[101],"attributable":[104],"limitations":[106],"dataset":[108],"collection":[109,171],"labeling":[111,173,194],"rather":[112,175],"than":[113,176],"sophistication":[114],"tools.":[117],"Specifically,":[118],"we":[119],"simple":[122],"decision":[123,127],"rules":[124],"\u2014":[125,136],"shallow":[126],"trees":[128],"trained":[129],"a":[131],"small":[132],"number":[133],"features":[135],"near-state-of-the-art":[138],"most":[141],"available":[142],"datasets":[143],"even":[149],"when":[150],"combined":[151],"together,":[152],"do":[153],"generalize":[155],"well":[156],"out-of-sample":[158],"datasets.":[159],"Our":[160],"findings":[161],"reveal":[162],"predictions":[164],"highly":[166],"dependent":[167],"each":[169],"dataset\u2019s":[170],"procedures":[174,195],"fundamental":[177],"differences":[178],"between":[179],"humans.":[182],"results":[184],"have":[185],"important":[186],"implications":[187],"both":[189],"transparency":[190],"sampling":[192],"potential":[197],"biases":[198],"using":[201],"pre-processing.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-04-27T00:00:00"}