{"id":"W4388422667","doi":"10.18280/isi.280530","title":"Leveraging Latent Dirichlet Allocation for Feature Extraction in User Comments: Enhancements to User-Centered Design in Indonesian Financial Technology","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Indonesian; Computer science; Dirichlet distribution; Topic model; Data mining; Information retrieval; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0007082648,0.000194111,0.0002552494,0.001920281,0.000143253,0.0001748929,0.0005065682,0.0001800729,0.000001442094],"category_scores_gemma":[0.0003135814,0.000213848,0.00004475993,0.002950838,0.0000248453,0.004647336,0.0001731722,0.000180293,0.00003271117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008063319,"about_ca_system_score_gemma":0.00006684798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005072318,"about_ca_topic_score_gemma":0.00007255331,"domain_scores_codex":[0.9983658,0.0000694713,0.0006353962,0.0002631698,0.0002425482,0.0004236481],"domain_scores_gemma":[0.9990612,0.00007165672,0.000281473,0.0003516555,0.0001877789,0.00004625944],"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":[0.0003171073,0.0003468409,0.07204185,0.0004239221,0.00007256794,0.00002463664,0.01756588,0.04568104,0.01791826,0.01877997,0.006986601,0.8198413],"study_design_scores_gemma":[0.005903257,0.0009147956,0.377097,0.001899832,0.00003935679,0.00003120909,0.001811927,0.3912483,0.1331414,0.06212579,0.023665,0.002122113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1312246,0.0000110603,0.8663075,0.0007970073,0.0001556208,0.001074115,0.000003976723,0.0003944283,0.00003170805],"genre_scores_gemma":[0.8977408,0.00002360511,0.1009546,0.0003537323,0.00001681352,0.000750814,0.0001139895,0.00001114654,0.00003451476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8177192,"threshold_uncertainty_score":0.872047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02612105426512728,"score_gpt":0.2924625459688797,"score_spread":0.2663414917037524,"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."}}