{"id":"W2945558385","doi":"10.1007/978-3-030-15130-0_8","title":"Performance Analysis of a Serial Natural Language Processing Pipeline for Scaling Analytics of Academic Writing Process","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Pipeline (software); Writing process; Process (computing); Analytics; Scalability; Academic writing; Data science; Natural language processing; Mathematics education; Programming language; Database; Psychology","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":[0.001296577,0.0009578189,0.0005668387,0.001126915,0.0005394359,0.001276121,0.001179052,0.0006524993,0.006716653],"category_scores_gemma":[0.005820197,0.0003525635,0.0004165306,0.001616876,0.0003978245,0.001420713,0.0007418823,0.000809364,0.002172908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009828204,"about_ca_system_score_gemma":0.002058764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01501971,"about_ca_topic_score_gemma":0.009297627,"domain_scores_codex":[0.9991211,0.0001494056,0.00006937387,0.0002252585,0.0003258151,0.000109062],"domain_scores_gemma":[0.9950985,0.002726961,0.0001742408,0.0005200281,0.001270164,0.0002100789],"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":[0.006598002,0.001667943,0.01990938,0.0005084805,0.0002304449,0.0003708919,0.0005379376,0.1100317,0.1319159,0.005890302,0.03048514,0.6918539],"study_design_scores_gemma":[0.00007498755,0.0005227868,0.005034248,0.000009293863,0.00004294599,0.00007198111,0.00008770511,0.9379517,0.05276568,0.001459537,0.001951356,0.00002771633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.685773,0.0008915384,0.2653153,0.0005534909,0.0002904195,0.0003954646,0.002888505,0.0360674,0.007824929],"genre_scores_gemma":[0.8291993,0.0002055104,0.1595015,0.0001792824,0.00008313616,0.0002232439,0.004413564,0.0005337799,0.005660752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01501971,"threshold_uncertainty_score":0.02986461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0235048700727326,"score_gpt":0.2933845268541546,"score_spread":0.269879656781422,"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."}}