{"id":"W1574923366","doi":"10.1002/widm.1112","title":"Self‐organizing maps for latent semantic analysis of free‐form text in support of public policy analysis","year":2013,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Mitacs; University of Victoria","keywords":"Computer science; Cluster analysis; Information retrieval; Unstructured data; Latent semantic analysis; Context (archaeology); Topic model; Document clustering; Natural language processing; Artificial intelligence; Big data; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001375656,0.0003633696,0.001943816,0.001877415,0.0001135534,0.0001334243,0.001161774,0.00006670981,0.0002546074],"category_scores_gemma":[0.00007278374,0.0003013354,0.0007473648,0.004503287,0.0001253261,0.001085718,0.003079879,0.0001319054,0.000006282533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005881788,"about_ca_system_score_gemma":0.00012666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003854542,"about_ca_topic_score_gemma":0.0009739334,"domain_scores_codex":[0.9969183,0.0001850253,0.001577994,0.0007276376,0.0001548657,0.0004362459],"domain_scores_gemma":[0.9967633,0.0002730411,0.0007897103,0.001878644,0.0001759166,0.000119313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002680745,0.001403488,0.7903975,0.001055179,0.0143911,0.000001289161,0.006388901,0.00002618128,0.0003722328,0.002148237,0.03905642,0.1447327],"study_design_scores_gemma":[0.004992683,0.001683071,0.3096922,0.005199911,0.1096078,0.000009728428,0.01495937,0.482829,0.0008410129,0.01629221,0.04842136,0.005471694],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9304622,0.01294264,0.04372816,0.0008178711,0.0001305467,0.002230674,0.004265287,0.00009229166,0.005330328],"genre_scores_gemma":[0.9896929,0.0008362564,0.004330356,0.0000151807,0.0001438698,0.0001423217,0.004556419,0.00002911658,0.0002536091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4828028,"threshold_uncertainty_score":0.9999439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05294647992264497,"score_gpt":0.3458112725074737,"score_spread":0.2928647925848287,"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."}}