{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002919586,0.000868012,0.0009218038,0.004722957,0.001189353,0.002552938,0.001685093,0.001208834,0.002490382],"category_scores_gemma":[0.01613243,0.0005259514,0.001461376,0.003663651,0.001307225,0.002840703,0.002347181,0.001968912,0.001500433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001401091,"about_ca_system_score_gemma":0.001616785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004308277,"about_ca_topic_score_gemma":0.00451024,"domain_scores_codex":[0.9979199,0.0009841796,0.000130452,0.0003624287,0.0004762148,0.0001267981],"domain_scores_gemma":[0.9911465,0.006623557,0.0005703642,0.0006457891,0.0008753123,0.000138511],"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":[0.0003227226,0.0002290649,0.005114338,0.0004544378,0.0002785299,0.0003487852,0.001548738,0.3571495,0.004159722,0.1319693,0.0139143,0.4845105],"study_design_scores_gemma":[0.000009952957,0.00001321477,0.0005855648,0.00001929608,0.00001223163,0.00003338703,0.0001653764,0.8994825,0.001029776,0.09638742,0.002244008,0.00001725243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007796889,0.0002103015,0.9897534,0.0002594542,0.0000335144,0.00007662829,0.0003172146,0.0008163222,0.000736207],"genre_scores_gemma":[0.2545559,0.0004644914,0.739115,0.0001464337,0.0001835989,0.0007006256,0.002145608,0.0003424056,0.002345846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004722957,"threshold_uncertainty_score":0.0154404,"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."}}