{"id":"W3086839491","doi":"10.1145/3396956.3401801","title":"Bot detection in twitter landscape using unsupervised learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Limelight; Computer science; Cluster analysis; Principal component analysis; Social media; Set (abstract data type); Sentiment analysis; Big data; Data set; Data science; Fake news; Component (thermodynamics); Artificial intelligence; Data mining; World Wide Web; Internet privacy; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001164576,0.00006361899,0.00007109638,0.00006721092,0.00006456884,0.0001141465,0.0001675542,0.0000425427,0.00003980199],"category_scores_gemma":[0.00003578439,0.00006016983,0.00002591577,0.0004840525,0.000004530583,0.0003456487,0.00006470671,0.0001722095,0.00004558493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001844378,"about_ca_system_score_gemma":0.00001197326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001279194,"about_ca_topic_score_gemma":0.00002863889,"domain_scores_codex":[0.999384,0.00005574556,0.0001054138,0.0002158983,0.0001084762,0.0001303979],"domain_scores_gemma":[0.999792,0.00002320657,0.00002353343,0.00009348648,0.00001620167,0.00005154206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001099924,0.00009061232,0.1174888,0.00008108567,0.00003341414,0.00008205361,0.02054857,0.05864626,0.5540983,0.0008743914,0.0004939082,0.2474526],"study_design_scores_gemma":[0.0002674872,0.00007332096,0.005619644,0.000005685383,0.000001485808,0.000006658432,0.00007931926,0.9747506,0.01804193,0.00009651928,0.0009551651,0.0001021791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5112831,0.00001579036,0.486968,0.0005106722,0.0001348463,0.0000370069,1.844871e-8,0.0001646677,0.0008859498],"genre_scores_gemma":[0.9946336,0.000001699536,0.004470488,0.0007511929,0.0001025434,0.000001637637,2.369664e-7,0.000005200692,0.00003347112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9161043,"threshold_uncertainty_score":0.2453654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04186545355463848,"score_gpt":0.2389900483098186,"score_spread":0.1971245947551802,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}