{"id":"W3017310594","doi":"10.1504/ijcse.2020.10028620","title":"User content categorisation model, a generic model that combines text mining and semantic models","year":2020,"lang":"en","type":"article","venue":"International Journal of Computational Science and Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Montréal","funders":"","keywords":"Computer science; User-generated content; Content (measure theory); Meaning (existential); Information retrieval; User modeling; World Wide Web; Social media; User interface","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":[],"consensus_categories":[],"category_scores_codex":[0.0003865097,0.0001002458,0.0001410178,0.0002137904,0.00007064888,0.0003395132,0.0005027271,0.00002334795,3.939892e-7],"category_scores_gemma":[0.00004216029,0.00008687344,0.00003093016,0.0001970431,0.00004504259,0.001723298,0.0001707084,0.00007561417,2.0678e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005488218,"about_ca_system_score_gemma":0.0001322779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006256078,"about_ca_topic_score_gemma":3.711673e-7,"domain_scores_codex":[0.9986811,0.000007999797,0.0002862652,0.0001767012,0.0007244723,0.0001234881],"domain_scores_gemma":[0.9990352,0.00005368193,0.0001616714,0.00004894342,0.0005605407,0.0001399111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003894841,0.000009230852,0.0001649732,0.000007985137,0.00001821409,0.000006029383,0.001093988,0.9618968,0.002144916,0.02991619,0.0001206899,0.004617132],"study_design_scores_gemma":[0.0002182856,0.00003685265,0.0005809043,0.00003667774,0.000003615872,0.0001462739,0.00004693677,0.9914845,0.000300225,0.007016477,0.00003460644,0.0000946935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1869317,0.0001311971,0.8101614,0.002500138,0.0001557277,0.00004191868,9.700176e-7,0.0000278248,0.00004917222],"genre_scores_gemma":[0.8529829,0.00004631573,0.146513,0.0003937158,0.00005316674,0.000001902919,5.149413e-7,0.000004587466,0.000003870251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6660512,"threshold_uncertainty_score":0.3542596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0723288038854928,"score_gpt":0.2548607681570726,"score_spread":0.1825319642715799,"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."}}