{"id":"W4313591642","doi":"10.1108/ijpcc-09-2022-0312","title":"Weighted ensemble classifier for malicious link detection using natural language processing","year":2023,"lang":"en","type":"article","venue":"International Journal of Pervasive Computing and Communications","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Classifier (UML); Phishing; Machine learning; Artificial intelligence; The Internet; Feature selection; Malware; Feature extraction; Data mining; Information retrieval; World Wide Web; Computer security","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":[0.001307478,0.0009280324,0.001176916,0.003165025,0.0006629596,0.0009480471,0.001110481,0.001152729,0.001373057],"category_scores_gemma":[0.003344932,0.0002274088,0.0009298982,0.001169851,0.0003157071,0.001448233,0.0005259986,0.001358473,0.001071614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006722942,"about_ca_system_score_gemma":0.0009117533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004877148,"about_ca_topic_score_gemma":0.005828511,"domain_scores_codex":[0.9988757,0.000161017,0.0001241703,0.0002675042,0.0004166966,0.0001549197],"domain_scores_gemma":[0.998175,0.0007044493,0.0001960882,0.0001396945,0.0007217024,0.00006299157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004279671,0.0009596167,0.01148008,0.0001751516,0.0002131616,0.0006570974,0.0001189911,0.1313306,0.02337512,0.00228501,0.01010817,0.8188691],"study_design_scores_gemma":[0.000006151809,0.00007938753,0.001207389,0.000009974996,0.00003675734,0.0001043657,0.000024198,0.9915857,0.004991334,0.0009842823,0.0009574057,0.0000130469],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1926344,0.00150566,0.7927711,0.0006899619,0.0004262942,0.0003570773,0.0008571051,0.004873352,0.005885171],"genre_scores_gemma":[0.8127074,0.0004586828,0.1765117,0.0003169799,0.000282824,0.000233952,0.002679408,0.00009616307,0.006712848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004877148,"threshold_uncertainty_score":0.009697497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04321118908304183,"score_gpt":0.3465499600806845,"score_spread":0.3033387709976427,"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."}}