{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001511801,0.001077566,0.0006936061,0.001856321,0.0005753159,0.001114617,0.0008445551,0.0007770609,0.003636415],"category_scores_gemma":[0.003418917,0.0001944652,0.000730683,0.001551311,0.0003296825,0.001256217,0.0008363202,0.001133728,0.002040003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000343054,"about_ca_system_score_gemma":0.0009430071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002712517,"about_ca_topic_score_gemma":0.004407901,"domain_scores_codex":[0.9992748,0.0002069051,0.000105084,0.0001479446,0.0001785247,0.00008669709],"domain_scores_gemma":[0.9970892,0.001224458,0.0001809239,0.0002934657,0.001083333,0.0001286898],"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":[0.001304219,0.0009962281,0.008147872,0.0003793091,0.0001334181,0.0003149644,0.0002820127,0.01796324,0.05423262,0.00107879,0.01699073,0.8981767],"study_design_scores_gemma":[0.00009713801,0.000570487,0.01007563,0.00006304877,0.0003005689,0.0002713586,0.0003552805,0.8916302,0.08010573,0.001938008,0.01454958,0.00004299388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7242171,0.00502545,0.2323464,0.002119365,0.002798036,0.0004969116,0.003959613,0.01493329,0.01410385],"genre_scores_gemma":[0.8421351,0.0008209396,0.1351185,0.0003340645,0.000882254,0.0002912788,0.008125443,0.000278648,0.01201386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003636415,"threshold_uncertainty_score":0.01216501,"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."}}