{"id":"W4415360535","doi":"10.59934/jaiea.v5i1.1643","title":"Application of Sentiment Analysis to Crime News using Tf-Idf and K-Nearest Neighbor to Assess Public Perception","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Sentiment analysis; Public opinion; Perception; Social media; Recall; Preprocessor; Term (time); Crime scene; Feature (linguistics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009051985,0.0002795941,0.0006400674,0.002304576,0.0002611953,0.0006029821,0.0005642057,0.000121551,0.00002588378],"category_scores_gemma":[0.00008714698,0.0002959059,0.0002585225,0.005000422,0.00006058681,0.0004736111,0.0002669871,0.0002296016,0.000011756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000148791,"about_ca_system_score_gemma":0.0001267317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159477,"about_ca_topic_score_gemma":0.00002009521,"domain_scores_codex":[0.9971139,0.00005622771,0.001503709,0.0005389837,0.0004487238,0.0003384407],"domain_scores_gemma":[0.9977083,0.0001551048,0.0005312427,0.0005328976,0.000720039,0.0003523839],"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":[0.00003431394,0.0003891081,0.005295305,0.0001246903,0.001242929,0.000001472854,0.001627546,0.3421994,0.1255855,0.03284685,0.00006704347,0.4905858],"study_design_scores_gemma":[0.00004528616,0.0001235167,0.0118632,0.0001260703,0.0009271376,0.000006808593,0.001165153,0.9737964,0.008904558,0.0003299975,0.002420041,0.000291845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1164595,0.0004588095,0.880879,0.001578754,0.0001819726,0.0003918835,0.000005937326,0.00001521934,0.0000289727],"genre_scores_gemma":[0.9218547,0.0002395707,0.07751752,0.0001161769,0.0001929578,0.00003063213,0.000004093408,0.0000129443,0.00003142534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8053952,"threshold_uncertainty_score":0.9999493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06893804411035655,"score_gpt":0.3403690342731577,"score_spread":0.2714309901628011,"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."}}