{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002910654,0.0000645842,0.00009591725,0.0004146868,0.0002353101,0.001007838,0.0009070123,0.00002491299,0.00001020865],"category_scores_gemma":[0.0002287427,0.00004125169,0.000006995371,0.001738927,0.0002910257,0.02165475,0.001477603,0.00009242595,0.00007458781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008135339,"about_ca_system_score_gemma":0.00004398507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001414662,"about_ca_topic_score_gemma":0.000002005229,"domain_scores_codex":[0.9987872,0.00000905678,0.0003245373,0.0001307538,0.0005919079,0.0001565071],"domain_scores_gemma":[0.9985903,0.0000548343,0.0001501449,0.0005307516,0.0006585035,0.00001546913],"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":[0.00006870864,0.00003088013,0.01974883,0.0009746867,0.00001062896,2.613696e-8,0.002761365,0.001573223,0.0001578374,0.4142021,0.01041799,0.5500538],"study_design_scores_gemma":[0.0001564569,0.00001130262,0.1855877,0.00002310988,0.000003599447,0.000002351446,0.0007270033,0.6923372,0.00002765658,0.0005299176,0.120481,0.0001127651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5366729,0.00003129655,0.4140766,0.001326424,0.0006000384,0.0009239888,0.00003889376,0.00004403327,0.04628589],"genre_scores_gemma":[0.9961204,0.00001266568,0.002468,0.001249617,0.00006963355,0.000001954595,0.00006978812,0.000001083931,0.000006858245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.690764,"threshold_uncertainty_score":0.9920288,"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."}}