{"id":"W3000358430","doi":"10.1016/j.cose.2020.101716","title":"A semantic-based classification approach for an enhanced spam detection","year":2020,"lang":"en","type":"article","venue":"Computers & Security","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Categorization; Text categorization; Domain (mathematical analysis); Information retrieval; Bag-of-words model; Set (abstract data type); Semantic analysis (machine learning); Artificial intelligence; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009847854,0.0007659252,0.0008860146,0.003670984,0.001025222,0.001389916,0.001013235,0.00150437,0.002812453],"category_scores_gemma":[0.001737561,0.0002158833,0.001216509,0.001968024,0.000556311,0.001906035,0.00111055,0.0009016349,0.001932051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006584266,"about_ca_system_score_gemma":0.001167282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002609462,"about_ca_topic_score_gemma":0.003808496,"domain_scores_codex":[0.9987769,0.0001819415,0.00008870148,0.0002262746,0.0005837472,0.0001423952],"domain_scores_gemma":[0.9990309,0.0001501729,0.00005162884,0.0001075621,0.0006096083,0.00004997429],"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":[0.0005389274,0.001081729,0.005699321,0.0002606431,0.0001871293,0.0002674602,0.0002332807,0.01299719,0.1066333,0.0188004,0.01112065,0.8421799],"study_design_scores_gemma":[0.00003282679,0.0003315671,0.006335113,0.00006342083,0.0002432115,0.0006086376,0.0002166522,0.9112495,0.0415017,0.02333117,0.01601004,0.00007618217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0443475,0.0006373179,0.9442947,0.000509347,0.0003215051,0.0002268224,0.0004473467,0.00262991,0.006585546],"genre_scores_gemma":[0.4823981,0.0004565307,0.5061788,0.0004290145,0.0003567728,0.000209279,0.00145714,0.0001615831,0.008352853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003670984,"threshold_uncertainty_score":0.009408593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04376752072950654,"score_gpt":0.2557178883192978,"score_spread":0.2119503675897913,"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."}}