{"id":"W4408745144","doi":"10.23977/aetp.2025.090120","title":"A Study of Second Language Vocabulary Acquisition Based on Corpus Linguistics","year":2025,"lang":"en","type":"article","venue":"Advances in Educational Technology and Psychology","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Linguistics; Corpus linguistics; Vocabulary; Applied linguistics; Computer science; Second-language acquisition; Natural language processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372305,0.000241579,0.0003852705,0.002796261,0.001576982,0.002395674,0.0003899135,0.0004854019,0.001695781],"category_scores_gemma":[0.005736844,0.0002515494,0.0001798605,0.003132679,0.002376431,0.004366875,0.001610096,0.0009433369,0.0002257598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048863,"about_ca_system_score_gemma":0.002266839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00202794,"about_ca_topic_score_gemma":0.004188284,"domain_scores_codex":[0.9990566,0.000567249,0.0000551785,0.000115355,0.0001591013,0.00004655544],"domain_scores_gemma":[0.9942443,0.004703231,0.0003364424,0.0002168597,0.0003029742,0.000196192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001065108,0.0006217459,0.06932962,0.001882926,0.00004540276,0.001980049,0.1302614,0.000819486,0.01721731,0.3293642,0.003821145,0.4445502],"study_design_scores_gemma":[0.00008105842,0.001298995,0.2883859,0.003448023,0.0001041589,0.008382439,0.1486848,0.006865607,0.01762368,0.1670569,0.3578436,0.0002248403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8308581,0.01511641,0.03406841,0.003740013,0.0001501433,0.0004943407,0.0003602323,0.00006623633,0.1151461],"genre_scores_gemma":[0.9635837,0.007871999,0.02048433,0.000340087,0.00006094116,0.0003789101,0.000213698,0.00004268534,0.007023556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002796261,"threshold_uncertainty_score":0.007610083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009847614990049332,"score_gpt":0.3778815165353407,"score_spread":0.3680339015452914,"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."}}