{"id":"W2982573935","doi":"10.5539/cis.v12n4p84","title":"A Text and Data Analytics Approach to Enrich the Quality of Unstructured Research Information","year":2019,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Unstructured data; Data science; Context (archaeology); Process (computing); Quality (philosophy); Information retrieval; Information quality; Filter (signal processing); Knowledge extraction; Information system; Data mining; Knowledge management; Big data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009649694,0.001251201,0.001039965,0.01954873,0.001335447,0.006995437,0.001639986,0.001185917,0.002457806],"category_scores_gemma":[0.02228045,0.0004165445,0.001515279,0.01906976,0.002207005,0.01007894,0.00259906,0.001740106,0.0008789858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001947674,"about_ca_system_score_gemma":0.003027327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002146865,"about_ca_topic_score_gemma":0.002905858,"domain_scores_codex":[0.9934518,0.002255559,0.000941286,0.0009392021,0.002269376,0.0001428005],"domain_scores_gemma":[0.9715132,0.01629454,0.003266095,0.00302017,0.005393261,0.00051273],"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":[0.000286056,0.0003787636,0.0106073,0.00305995,0.000279888,0.001314184,0.006949014,0.007306759,0.01669666,0.1419102,0.01549479,0.7957165],"study_design_scores_gemma":[0.0001366462,0.0003772162,0.01494303,0.002321679,0.0006538768,0.001708517,0.008529638,0.1984017,0.03378019,0.433758,0.305081,0.0003085098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01305736,0.002235786,0.9613699,0.005146204,0.0002708196,0.0008076046,0.002820908,0.001981535,0.01230989],"genre_scores_gemma":[0.0779921,0.001559369,0.9140612,0.0005065908,0.0002784781,0.0003967979,0.002245679,0.0001378986,0.002821908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01954873,"threshold_uncertainty_score":0.05103308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2214000277885303,"score_gpt":0.3900992289721755,"score_spread":0.1686992011836451,"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."}}