{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006991831,0.0002994484,0.0009376821,0.0006618283,0.00007754101,0.00005112404,0.0007739839,0.0002754482,0.00001430323],"category_scores_gemma":[0.00005266129,0.0002598228,0.0003649347,0.0003255653,0.0000414658,0.000324096,0.0001437007,0.0004941391,0.000002767554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005429897,"about_ca_system_score_gemma":0.0002171016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001412583,"about_ca_topic_score_gemma":0.000003752282,"domain_scores_codex":[0.9976825,0.00001321572,0.00101727,0.0005017217,0.0004973676,0.0002879469],"domain_scores_gemma":[0.9975072,0.0001416311,0.001236496,0.0003494075,0.0007226353,0.00004260665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003174325,0.00008791264,0.005766559,0.02029102,0.004461627,0.00001346134,0.01843641,0.2789299,0.0084554,0.3369523,0.000119024,0.3261689],"study_design_scores_gemma":[0.0001775156,0.00005151135,0.00005091341,0.001543686,0.0004822217,0.000002677301,0.0002382804,0.9939877,0.002576725,0.00003858441,0.000519763,0.0003304477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03500138,0.00335531,0.8978294,0.00004538824,0.0008982894,0.001137062,0.00005204221,0.0002196114,0.06146149],"genre_scores_gemma":[0.7970116,0.00001950462,0.005423316,0.00001989038,0.0002996161,0.000003745212,0.00002892678,0.00003082636,0.1971626],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8924061,"threshold_uncertainty_score":0.9999854,"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."}}