{"id":"W2794992239","doi":"10.1108/lht-10-2017-0211","title":"Text mining based theme logic structure identification: application in library journals","year":2018,"lang":"en","type":"article","venue":"Library Hi Tech","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Originality; Theme (computing); Knowledge extraction; Data science; Big data; Artificial neural network; Mode (computer interface); Identification (biology); Artificial intelligence; Knowledge management; Data mining; Sociology; Social science; World Wide Web; Qualitative research","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001206375,0.0001937706,0.0001748299,0.0004798706,0.000173987,0.0007814628,0.0008138269,0.0001483372,0.005423802],"category_scores_gemma":[0.00004095897,0.0001673601,0.00004514998,0.001761909,0.0001069345,0.008916724,0.0002669569,0.0001834393,0.0004967782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006657262,"about_ca_system_score_gemma":0.00003734375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001554069,"about_ca_topic_score_gemma":0.000006857864,"domain_scores_codex":[0.9986531,0.00001337281,0.0004279052,0.0004073882,0.0002307405,0.0002674955],"domain_scores_gemma":[0.999086,0.00003914038,0.0002906174,0.0005221757,0.00004620491,0.00001587587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002151871,0.0003368718,0.5109402,0.0004955183,0.00003133979,0.0000359134,0.0001142314,0.00007589648,0.02760398,0.08983915,0.1626823,0.2076295],"study_design_scores_gemma":[0.0005032228,0.00002022162,0.2224885,0.0003461641,0.00003475039,0.00001042408,0.0001917485,0.02170879,0.02846758,0.07845675,0.6469778,0.0007940489],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8089228,0.001605888,0.03190194,0.0388843,0.002004889,0.001705904,0.0001405744,0.00236496,0.1124687],"genre_scores_gemma":[0.9894302,0.00002471837,0.002386838,0.004937657,0.002106241,0.00002640359,0.0003879823,0.00004536035,0.000654557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4842955,"threshold_uncertainty_score":0.9954854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04854344764614971,"score_gpt":0.280002269096045,"score_spread":0.2314588214498953,"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."}}