{"id":"W4292621974","doi":"10.1145/3546157.3546173","title":"N-gram and Word2Vec Feature Engineering Approaches for Spam Recognition on Some Influential Twitter Topics in Saudi Arabia","year":2022,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Word2vec; Social media; Computer science; Sentiment analysis; Artificial intelligence; Arabic; Machine learning; Feature engineering; Feature (linguistics); Random forest; n-gram; Data science; World Wide Web; Deep learning; Language model","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":[0.0004181925,0.0009422429,0.0004810455,0.00174328,0.000559958,0.0004584743,0.0003622643,0.0005073478,0.0008590299],"category_scores_gemma":[0.00139768,0.0001208801,0.0005554071,0.001057002,0.0002340488,0.000632689,0.0004475227,0.0004613738,0.0007669926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003815577,"about_ca_system_score_gemma":0.0004651363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01511816,"about_ca_topic_score_gemma":0.01708283,"domain_scores_codex":[0.9996777,0.00006847924,0.00003676654,0.00006094115,0.00007037434,0.00008564936],"domain_scores_gemma":[0.9994926,0.0001195239,0.00005653491,0.00004490507,0.0002496062,0.00003678807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001646135,0.0008158718,0.07781947,0.0003461074,0.0002368029,0.001209797,0.001041559,0.04761694,0.03462731,0.001417867,0.0255498,0.8076723],"study_design_scores_gemma":[0.00004476825,0.0001941936,0.03120012,0.00002697661,0.00008404644,0.0003370998,0.001393368,0.9398503,0.02022334,0.001243274,0.005362022,0.00004043795],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9318984,0.001250945,0.05897642,0.0006037468,0.0001980083,0.0001279303,0.002267456,0.002059426,0.002617765],"genre_scores_gemma":[0.9503642,0.0003866262,0.03868029,0.0001348118,0.00009213615,0.00007762994,0.007201156,0.00006514294,0.002998013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01511816,"threshold_uncertainty_score":0.03006029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03637850094376847,"score_gpt":0.2177338790444393,"score_spread":0.1813553781006708,"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."}}