{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004635203,0.0000854081,0.0001189148,0.0003033988,0.0003639579,0.0002781079,0.001011386,0.00004799771,5.463059e-7],"category_scores_gemma":[0.0001596156,0.00008072448,0.00008798078,0.0003056986,0.0000452645,0.000375418,0.0003028332,0.0002437054,0.000001993923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000768809,"about_ca_system_score_gemma":0.00007341088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003018245,"about_ca_topic_score_gemma":0.00002314646,"domain_scores_codex":[0.9991292,0.00008174361,0.0003146926,0.000123765,0.0002241952,0.0001263914],"domain_scores_gemma":[0.998221,0.0003359581,0.0003486016,0.0002530403,0.0007959501,0.0000454902],"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":[0.00002652993,0.00004000167,0.0005292608,0.00001696275,0.0001043276,0.00001107657,0.005344535,0.0005646615,0.03083621,0.001381386,0.00009548962,0.9610496],"study_design_scores_gemma":[0.0004382786,0.00006166446,0.002502436,0.0001391846,0.00001934243,0.0003290524,0.0005065707,0.9901555,0.002357276,0.001563508,0.001817448,0.0001097482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3947297,0.0014951,0.5985749,0.003740906,0.001195496,0.00008754597,0.000002505087,0.00009731705,0.00007658076],"genre_scores_gemma":[0.9596999,0.00009673677,0.03960316,0.0001581088,0.0003890595,0.000002076366,0.00000543671,0.000008670255,0.00003686288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9895908,"threshold_uncertainty_score":0.3291849,"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."}}