{"id":"W4306178485","doi":"10.3233/jid-220013","title":"Natural language processing (NLP) aided qualitative method in health research","year":2022,"lang":"en","type":"article","venue":"Journal of Integrated Design and Process Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University; Alberta Health Services; Concordia University; University of Calgary","funders":"","keywords":"Computer science; Natural language processing; Sentence; Cluster analysis; Artificial intelligence; Workload; Context (archaeology); Automatic summarization; Qualitative research; Information retrieval; Text mining; Data science; Data mining","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.06778664,0.00007748484,0.0002444322,0.001015889,0.001620364,0.0002253929,0.0005472592,0.00002059118,0.00006593845],"category_scores_gemma":[0.003842853,0.00005835735,0.00003798657,0.005815874,0.0006215968,0.0006571188,0.00005781788,0.0008443847,4.501537e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004572506,"about_ca_system_score_gemma":0.00551518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001038099,"about_ca_topic_score_gemma":0.0001211412,"domain_scores_codex":[0.9913536,0.0058123,0.0004854101,0.0002203177,0.001751236,0.0003771363],"domain_scores_gemma":[0.9963799,0.001584369,0.000393959,0.00004792781,0.001420294,0.0001735949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002253344,0.0001333892,0.000198294,0.0000432143,0.00001177429,0.00003839637,0.6586795,0.006182144,0.002561882,0.004363092,0.0001700944,0.3273929],"study_design_scores_gemma":[0.0004493449,0.0004613136,0.0003707524,0.0001604419,0.000006536657,0.00005873448,0.8696294,0.08643594,0.0007456653,0.04033119,0.001183956,0.0001666815],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3380183,0.0199121,0.6248225,0.01409986,0.0004655462,0.0006756596,0.000005237407,0.00003999702,0.001960816],"genre_scores_gemma":[0.9113969,0.00004431833,0.08806462,0.0001997412,0.00003915363,0.000007593708,4.527754e-7,0.000003819974,0.0002433972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5733786,"threshold_uncertainty_score":0.9996794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2305358605394815,"score_gpt":0.5988821724556453,"score_spread":0.3683463119161638,"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."}}