{"id":"W3037796656","doi":"10.1007/978-3-030-51517-1_31","title":"Machine Learning Classification Models with SPD/ED Dataset: Comparative Study of Abstract Versus Full Article Approach","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Artificial intelligence; Boosting (machine learning); Machine learning; Support vector machine; Decision tree; Gradient boosting; Random forest; Precision and recall; Context (archaeology); Recall","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":[0.0003919817,0.0003957959,0.0005191397,0.0004214283,0.0002054064,0.0003111706,0.002596138,0.0001557454,0.00000817896],"category_scores_gemma":[0.00003720627,0.0003218346,0.00004467387,0.0007040375,0.0005422813,0.0008911062,0.0007839472,0.0008434749,0.00001913513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355596,"about_ca_system_score_gemma":0.0001931254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002852243,"about_ca_topic_score_gemma":0.00004456113,"domain_scores_codex":[0.9968578,0.00004110898,0.0005255762,0.001321612,0.0009314745,0.0003224056],"domain_scores_gemma":[0.9976259,0.000290167,0.0005703946,0.001238815,0.0001763217,0.00009838948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004327158,0.0009026081,0.0002819608,0.00009909643,0.000137869,0.0000436726,0.008813753,0.5772651,0.00138768,0.1478148,0.00007454087,0.2627461],"study_design_scores_gemma":[0.0009800227,0.001153482,0.0002635564,0.00004501841,0.00001709125,0.000005781003,0.00002693262,0.9863724,0.0006576082,0.009910262,0.0001720301,0.0003958225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001407591,0.0001500692,0.9949098,0.000315715,0.0001619551,0.0006531386,0.00002130569,0.0002551182,0.002125329],"genre_scores_gemma":[0.8696558,0.00001356533,0.1301436,0.00004283415,0.00003429165,0.00001757602,0.00006057609,0.0000142653,0.00001737923],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8682483,"threshold_uncertainty_score":0.9999233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08655538543899494,"score_gpt":0.2932814416779184,"score_spread":0.2067260562389235,"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."}}