{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004497274,0.001888998,0.001801376,0.007901989,0.0007976815,0.002346962,0.002272604,0.001720304,0.003382314],"category_scores_gemma":[0.009341957,0.0002791809,0.001658324,0.00586053,0.0004769301,0.002721563,0.001162987,0.00154231,0.003594571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001465824,"about_ca_system_score_gemma":0.00132265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0126005,"about_ca_topic_score_gemma":0.01605798,"domain_scores_codex":[0.9965549,0.0008843585,0.0005283609,0.0005995379,0.001206927,0.0002259522],"domain_scores_gemma":[0.9913783,0.00410344,0.0005029716,0.00169657,0.001944124,0.0003746031],"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":[0.003905185,0.006224681,0.05894591,0.004159864,0.001142448,0.0009242294,0.000240534,0.0580806,0.005620048,0.002189207,0.2600374,0.5985299],"study_design_scores_gemma":[0.0009274848,0.002349359,0.07029784,0.0005603138,0.0007349465,0.001749678,0.001369393,0.8000001,0.02069458,0.004619026,0.09637091,0.0003264241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6964497,0.02141715,0.02999131,0.00394565,0.002251964,0.0009237714,0.2144344,0.01297502,0.01761102],"genre_scores_gemma":[0.3745644,0.004573666,0.09151069,0.0006166463,0.0006069287,0.0005415708,0.5193835,0.0004020494,0.007800572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0126005,"threshold_uncertainty_score":0.02505428,"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."}}