{"id":"W4409348514","doi":"10.1007/s40593-025-00472-y","title":"Predicting Online Education Dropout: A new Machine Learning Model based on Sentiment Analysis, Socio-demographic, and Behavioral Data","year":2025,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence in Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université TÉLUQ; Université de Sherbrooke","funders":"","keywords":"Dropout (neural networks); Sentiment analysis; Computer science; Educational technology; Machine learning; Artificial intelligence; Online learning; Psychology; Data science; Mathematics education; Multimedia","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":[],"consensus_categories":[],"category_scores_codex":[0.0006774126,0.0001301992,0.0001913384,0.00158215,0.00008128948,0.0002726923,0.001049238,0.00006376136,0.00001068264],"category_scores_gemma":[0.0003036199,0.000129547,0.00009343376,0.0009176445,0.00004047967,0.0005164205,0.0001533705,0.0004793879,0.000001757779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001708854,"about_ca_system_score_gemma":0.001652683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004720595,"about_ca_topic_score_gemma":0.0002989646,"domain_scores_codex":[0.9982505,0.0001017919,0.0007198236,0.0003114249,0.0004820712,0.0001343318],"domain_scores_gemma":[0.9985535,0.000135638,0.0004581801,0.0002912071,0.0004742049,0.00008729922],"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":[0.00004206984,0.001928406,0.1444952,0.000006590998,0.0001237215,0.00000282533,0.0008832954,0.23422,0.0001299116,0.00927309,0.0001235983,0.6087713],"study_design_scores_gemma":[0.00004951798,0.00006923595,0.003116265,0.0001732598,0.0001059592,0.000004276984,0.0007468854,0.9717761,0.0001230616,0.02360863,0.0001321278,0.00009471708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3203981,0.0003014098,0.6552187,0.02247449,0.001427394,0.00008743339,0.000009418368,0.000024708,0.00005836181],"genre_scores_gemma":[0.9526627,0.0001002967,0.04625664,0.0003908264,0.0002826106,0.000001429918,0.00009188696,0.000005802059,0.0002078059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7375561,"threshold_uncertainty_score":0.5282775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0423147182675875,"score_gpt":0.404647021993181,"score_spread":0.3623323037255936,"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."}}