{"id":"W7115168809","doi":"10.18280/isi.301001","title":"Text Augmentation Approaches to Enhance Traditional Machine Learning Performance for SDGs Classification of Indonesian News Articles","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Universitas Gadjah Mada","keywords":"Indonesian; Training set; Key (lock); Support vector machine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008621473,0.0003643442,0.0004206936,0.001173877,0.0007432671,0.0006355049,0.0008540387,0.0002625305,0.00002489581],"category_scores_gemma":[0.0005333191,0.000390353,0.0001489927,0.002040256,0.000315302,0.006072504,0.000175696,0.0002659875,0.00006012161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005346675,"about_ca_system_score_gemma":0.0003185031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000044719,"about_ca_topic_score_gemma":0.00001870545,"domain_scores_codex":[0.9968001,0.0001214691,0.001666288,0.000441372,0.0005008787,0.0004699042],"domain_scores_gemma":[0.9974695,0.0002518884,0.001137398,0.0005775173,0.0004653102,0.00009839577],"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":[0.0001781504,0.0001260011,0.004701186,0.001094073,0.00006277849,6.361104e-8,0.006033868,0.002694179,0.00273891,0.1398553,0.0002861786,0.8422292],"study_design_scores_gemma":[0.00114145,0.0008228274,0.1016713,0.0008361538,0.00008266082,0.000005603696,0.005792529,0.7518856,0.1160211,0.01564863,0.005430377,0.0006617554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2574648,0.0001834405,0.7355075,0.002347068,0.0004064453,0.001414363,0.00004330725,0.0002576901,0.002375439],"genre_scores_gemma":[0.9752736,0.0001332322,0.02300267,0.0001714001,0.00004196119,0.0007319382,0.0002767856,0.00001310083,0.0003552926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8415675,"threshold_uncertainty_score":0.9998549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07416843936564876,"score_gpt":0.2659454558059801,"score_spread":0.1917770164403313,"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."}}