{"id":"W2493379773","doi":"10.1016/j.iheduc.2016.08.001","title":"Mining for gold: Identifying content-related MOOC discussion threads across domains through linguistic modeling","year":2016,"lang":"en","type":"article","venue":"The Internet and Higher Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Categorization; Computer science; Reliability (semiconductor); Set (abstract data type); Content analysis; Psychology; Natural language processing; Artificial intelligence","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":[0.0002542314,0.0001126755,0.0001148197,0.00002945203,0.0001393206,0.0002237276,0.0003519014,0.00005240482,0.000009731704],"category_scores_gemma":[0.00005772591,0.00005265757,0.00005399467,0.00009397986,0.00004903677,0.000253281,0.0001246014,0.00007969294,0.00001486494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003675791,"about_ca_system_score_gemma":0.00004077891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001018462,"about_ca_topic_score_gemma":0.00001370414,"domain_scores_codex":[0.9991523,0.00003585472,0.0002260681,0.0002602157,0.0001131541,0.00021242],"domain_scores_gemma":[0.9993862,0.0001170218,0.0001103323,0.0002485803,0.00009602406,0.00004184006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007972121,0.0003561369,0.007122992,0.0001366657,0.0002137796,0.000002504568,0.0810419,0.0003712325,0.005273408,0.6543135,0.00391013,0.247178],"study_design_scores_gemma":[0.002570819,0.0003441765,0.007486928,0.002572375,0.0001879765,0.00004174233,0.003797125,0.4419433,0.001112562,0.5053717,0.03351817,0.001053188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.680817,0.0005309565,0.2920447,0.02318842,0.002471372,0.0001788828,0.00000282935,0.0001323644,0.0006334822],"genre_scores_gemma":[0.9572513,0.00002877193,0.00453015,0.0001695058,0.0003200593,0.00001607578,0.000005500138,0.00001207554,0.03766658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.441572,"threshold_uncertainty_score":0.215741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06261479817410774,"score_gpt":0.3556481158414887,"score_spread":0.2930333176673809,"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."}}