{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002520181,0.0001658257,0.0001767504,0.00007270459,0.0002213869,0.0002654917,0.0006404109,0.0001055683,0.000001200564],"category_scores_gemma":[0.0000429916,0.0001773394,0.0001049763,0.0004970687,0.00003127378,0.0005710846,0.00006813784,0.0001689096,0.000008870608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005372889,"about_ca_system_score_gemma":0.00004591546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001948137,"about_ca_topic_score_gemma":0.000006425259,"domain_scores_codex":[0.9985601,0.0001124829,0.0002166733,0.0006610975,0.0002088792,0.0002408155],"domain_scores_gemma":[0.9990469,0.00007701892,0.0001293514,0.0004418585,0.0001198682,0.0001849684],"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":[0.0006858197,0.001551117,0.0004012048,0.00101637,0.0001380871,0.000006188731,0.02197628,0.02048871,0.3197951,0.02465392,0.00517503,0.6041122],"study_design_scores_gemma":[0.0005296177,0.0004614147,0.001102174,0.000007016807,0.000009762298,0.000002166361,0.00002508926,0.9620135,0.03335742,0.001117362,0.00116508,0.0002093292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03212957,0.00002109934,0.9652181,0.0007409312,0.0006071453,0.0004768367,0.000002877275,0.0006128065,0.0001906364],"genre_scores_gemma":[0.9157631,0.000001314143,0.08274621,0.001034827,0.0003603242,0.00005528903,0.00002462444,0.00001285914,0.000001386514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415249,"threshold_uncertainty_score":0.7231693,"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."}}