{"id":"W4315781748","doi":"10.18280/isi.270610","title":"Feature Extraction and Classification of Email Spam Detection Using IMTF-IDF+Skip-Thought Vectors","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Naive Bayes classifier; Support vector machine; Artificial intelligence; Feature extraction; tf–idf; Bag-of-words model; Convolutional neural network; Preprocessor; Pattern recognition (psychology); Classifier (UML); Feature (linguistics); Feature vector; Machine learning; Data mining; Term (time)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006308793,0.0008721115,0.0006296784,0.00249106,0.0002474409,0.0004716369,0.0004818646,0.0007001681,0.00183915],"category_scores_gemma":[0.001344819,0.0001302967,0.0007891543,0.0008971132,0.0001929179,0.0006697525,0.0003913057,0.0004150658,0.001115824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004825923,"about_ca_system_score_gemma":0.0003232216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004117859,"about_ca_topic_score_gemma":0.002745179,"domain_scores_codex":[0.999539,0.00006466827,0.00003779809,0.00009365366,0.0001564601,0.0001084063],"domain_scores_gemma":[0.9995485,0.0001068422,0.0000499529,0.00005503262,0.0002112624,0.00002838372],"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":[0.0006665828,0.0005285721,0.01609242,0.0001618984,0.00009564639,0.0003135212,0.0001019108,0.02288304,0.06420226,0.0009653961,0.007873235,0.8861155],"study_design_scores_gemma":[0.00002243349,0.0003508359,0.03065625,0.00002429647,0.00006711323,0.0004449902,0.00008778261,0.9070555,0.05714118,0.0007257235,0.003384773,0.00003906132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5765291,0.0009036356,0.4102623,0.0002861249,0.0002514216,0.0002648128,0.002021633,0.006099654,0.003381338],"genre_scores_gemma":[0.8555424,0.0002152688,0.1355884,0.00007147369,0.00006723109,0.000189911,0.003589023,0.00005791119,0.004678423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004117859,"threshold_uncertainty_score":0.008187771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01970955828636074,"score_gpt":0.2417364924723581,"score_spread":0.2220269341859974,"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."}}