{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006395554,0.0001467606,0.0001597607,0.0004239045,0.0007021359,0.0002407009,0.000230898,0.0001017532,0.0000113069],"category_scores_gemma":[0.0001099556,0.0001613098,0.00005889958,0.0009086952,0.00005727522,0.00438635,0.0001303493,0.0002591722,0.000005623311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004558527,"about_ca_system_score_gemma":0.00006669967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001459909,"about_ca_topic_score_gemma":0.00001925046,"domain_scores_codex":[0.9987026,0.0001461771,0.0003751044,0.0001890249,0.0003981895,0.0001889118],"domain_scores_gemma":[0.9988468,0.00006049014,0.0005651847,0.0002977508,0.0001754301,0.00005430099],"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":[0.0002565225,0.0001320791,0.007955404,0.0007358112,0.0001111439,0.000004418782,0.02313868,0.01391953,0.232199,0.01471842,0.0006110747,0.7062179],"study_design_scores_gemma":[0.0007836463,0.000510353,0.1065402,0.00009526895,0.00005429572,0.0006121504,0.002422127,0.8209246,0.04858413,0.003800714,0.01509089,0.0005816579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6292805,0.00009572737,0.3686313,0.00007070129,0.000973873,0.0002230961,0.00000712488,0.0001628625,0.0005547773],"genre_scores_gemma":[0.9939153,0.00001574944,0.005841772,0.00004115886,0.0000744588,0.00004236263,0.00002392319,0.000008951933,0.00003630347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.807005,"threshold_uncertainty_score":0.6578023,"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."}}