{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002540783,0.0009023899,0.0006015386,0.005780178,0.001604773,0.002097188,0.001297587,0.001302259,0.001988668],"category_scores_gemma":[0.01209514,0.0003612143,0.001237307,0.002494993,0.0006211447,0.002614133,0.002612824,0.001483219,0.001403229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008346237,"about_ca_system_score_gemma":0.00174959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007844169,"about_ca_topic_score_gemma":0.01407806,"domain_scores_codex":[0.9977539,0.0008814131,0.0001981585,0.0006176602,0.0003627116,0.000186224],"domain_scores_gemma":[0.9924741,0.004789744,0.0007423316,0.0006192522,0.0009468595,0.000427679],"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":[0.001986497,0.001929734,0.2369519,0.001785042,0.0006844308,0.0007435615,0.01190753,0.01417588,0.0387277,0.01498037,0.03797492,0.6381524],"study_design_scores_gemma":[0.0002203715,0.0007808993,0.0969229,0.0004920294,0.000530645,0.0004803725,0.01216694,0.7581401,0.02282926,0.05550181,0.0517308,0.0002039161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6745462,0.001771894,0.2898858,0.001955513,0.0004758486,0.00081331,0.01317532,0.007667955,0.009708084],"genre_scores_gemma":[0.85877,0.0002298775,0.1199373,0.0002267975,0.0001029027,0.0005847737,0.01572897,0.0003995756,0.004019795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007844169,"threshold_uncertainty_score":0.01559705,"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."}}