{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1339559,0.001729705,0.001834184,0.007627744,0.00392189,0.006050323,0.004004781,0.001792957,0.02123919],"category_scores_gemma":[0.1744137,0.001565687,0.001615454,0.009767845,0.006934411,0.004672901,0.007253109,0.004084722,0.004616252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006310608,"about_ca_system_score_gemma":0.0199154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005084215,"about_ca_topic_score_gemma":0.008799369,"domain_scores_codex":[0.8164564,0.1613568,0.008239961,0.006493032,0.006437418,0.001016366],"domain_scores_gemma":[0.7082444,0.2438751,0.009711579,0.01739353,0.01970423,0.001071198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001228031,0.000594031,0.003564489,0.02351106,0.0002782898,0.001410244,0.1663933,0.01005433,0.02135552,0.2156343,0.02638942,0.529587],"study_design_scores_gemma":[0.001109282,0.0007313686,0.006233791,0.009975049,0.000282158,0.001024298,0.07001269,0.06577872,0.03129664,0.4301246,0.3826133,0.0008179804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007187231,0.0004688476,0.9609296,0.001746621,0.000257083,0.0189776,0.002129784,0.0007674628,0.007535836],"genre_scores_gemma":[0.02134573,0.0002476665,0.9378156,0.00042292,0.00004380371,0.0383817,0.0004089121,0.0001976254,0.001135952],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1339559,"threshold_uncertainty_score":0.7084348,"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."}}