{"id":"W2954935485","doi":"10.1002/spy2.69","title":"Discerning cyber threatening incidents from ordinary events using sentiment analysis and logistic regression","year":2019,"lang":"en","type":"article","venue":"Security and Privacy","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Sentence; Set (abstract data type); Logistic regression; Event (particle physics); Precision and recall; Sentiment analysis; Natural language processing; Artificial intelligence; Recall; Data mining; Machine learning; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002932893,0.000181814,0.000342113,0.0002247918,0.0002320868,0.0002262064,0.0003156279,0.00006913422,0.0001097912],"category_scores_gemma":[0.0000205528,0.00015064,0.0001092791,0.0005045216,0.0000277302,0.0005477968,0.0009480237,0.0001408139,0.00001681723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000306103,"about_ca_system_score_gemma":0.00001444175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004945006,"about_ca_topic_score_gemma":0.00001515977,"domain_scores_codex":[0.9984918,0.000119086,0.0002665335,0.0005754703,0.000311493,0.0002356192],"domain_scores_gemma":[0.9992014,0.0001013679,0.0001902486,0.0003625073,0.0000325883,0.0001118663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001407315,0.00004399295,0.9874303,0.000016426,0.0004843443,0.00001444577,0.004330037,0.0001211868,0.001609436,0.0003278977,0.00001577138,0.005592108],"study_design_scores_gemma":[0.0009149557,0.00005851466,0.5402433,0.0002792608,0.0006289278,0.000009083512,0.0003552936,0.4486589,0.000735382,0.007288938,0.0003314222,0.0004960603],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802389,0.0009319341,0.0183439,0.0001245415,0.0001353427,0.00009792298,0.000003503635,0.00003596933,0.00008803088],"genre_scores_gemma":[0.9911355,0.0001119634,0.008538148,0.00005866649,0.00004345833,0.000001376868,0.00002281077,0.000006884892,0.00008117247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4485376,"threshold_uncertainty_score":0.614292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03226740322336508,"score_gpt":0.3019247693715464,"score_spread":0.2696573661481813,"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."}}