{"id":"W3093186001","doi":"10.1109/csp51677.2021.9357595","title":"SpaML: a Bimodal Ensemble Learning Spam Detector based on NLP Techniques","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Classifier (UML); Natural language processing; Ensemble learning; tf–idf; Set (abstract data type); Detector; Pattern recognition (psychology); Machine learning; Term (time)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00357417,0.001100476,0.001954008,0.004592252,0.001211231,0.001239478,0.001585706,0.001770552,0.001976194],"category_scores_gemma":[0.005888715,0.0004350008,0.0007154039,0.001472851,0.0006229399,0.003283888,0.00188895,0.001729983,0.002498675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005746512,"about_ca_system_score_gemma":0.000736873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009945967,"about_ca_topic_score_gemma":0.001731892,"domain_scores_codex":[0.9978368,0.000570872,0.00009408216,0.0003923379,0.0009412196,0.0001646705],"domain_scores_gemma":[0.9963952,0.001329887,0.000331041,0.0006043253,0.001134791,0.0002048045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004948556,0.0006689155,0.01609193,0.0001922758,0.0002567718,0.0002674393,0.0002244928,0.02709291,0.03030783,0.004285714,0.01589936,0.9042175],"study_design_scores_gemma":[0.00004037451,0.0003179953,0.003319112,0.00002935429,0.0000952435,0.0005277215,0.00006356062,0.9511481,0.02746576,0.006927253,0.01000491,0.00006067293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04183151,0.0007632033,0.9441608,0.0004439909,0.0001883103,0.0001817215,0.0002942085,0.00929061,0.002845637],"genre_scores_gemma":[0.4037479,0.0004800603,0.5838772,0.0009925385,0.000572966,0.0003718133,0.001681729,0.0005157033,0.007760182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004592252,"threshold_uncertainty_score":0.0189023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01738504715447093,"score_gpt":0.244266886106616,"score_spread":0.2268818389521451,"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."}}