{"id":"W4413230213","doi":"10.18280/isi.300606","title":"Performance Evaluation of Text Embedding Models for Ambiguity Classification in Indonesian News Corpus: A Comparative Study of TF-IDF, Word2Vec, FastText BERT, and GPT","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Word2vec; Ambiguity; Indonesian; Artificial intelligence; Natural language processing; Computer science; Information retrieval; Embedding; Linguistics; Philosophy","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":[0.001378546,0.0001397191,0.0002933786,0.0005244374,0.0001765981,0.0001079067,0.0003592047,0.0000656619,0.000001047437],"category_scores_gemma":[0.0001739399,0.0001422884,0.00002795085,0.0008460621,0.0000773382,0.002585531,0.0001215585,0.0001160088,0.000001839869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525042,"about_ca_system_score_gemma":0.0001657149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003264357,"about_ca_topic_score_gemma":0.0001361502,"domain_scores_codex":[0.9983546,0.0001606718,0.0008010563,0.0002089427,0.0003154637,0.0001592568],"domain_scores_gemma":[0.9982281,0.000162115,0.0006129689,0.000414165,0.0005522284,0.00003046865],"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":[0.00008053573,0.0002605278,0.02665568,0.0003553967,0.00004968361,3.260689e-8,0.05197224,0.08192484,0.0002455427,0.01499688,0.00008648757,0.8233722],"study_design_scores_gemma":[0.001133441,0.0001585443,0.124306,0.0001894212,0.00002889881,0.000001125678,0.00564911,0.8665447,0.0001949993,0.001638486,0.00005344639,0.0001018469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6987553,0.00002734581,0.2980877,0.00004001126,0.00004998626,0.001081465,0.000007944986,0.00003353159,0.001916721],"genre_scores_gemma":[0.9913015,0.00001222261,0.008078543,0.00002045883,0.000006005549,0.000494856,0.00006846795,0.00000381641,0.00001407136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8232703,"threshold_uncertainty_score":0.5802354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05522518239788383,"score_gpt":0.330857235527801,"score_spread":0.2756320531299172,"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."}}