{"id":"W2921441826","doi":"10.58729/1941-6679.1376","title":"Inside the Black Box of Dictionary Building for Text Analytics: A Design Science Approach","year":2019,"lang":"en","type":"article","venue":"Journal of international technology and information management","topic":"Information Systems Theories and Implementation","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Process (computing); Computer science; Analytics; Sustainability; Data science; Domain (mathematical analysis); Black box; Artificial intelligence","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":[0.002439396,0.00005011927,0.00009337814,0.0009331555,0.0002455835,0.00008523923,0.0003706171,0.00004149751,0.00002759457],"category_scores_gemma":[0.0001487836,0.00003643847,0.00003911815,0.0005028339,0.0003405301,0.002670888,0.00006787068,0.00007230329,0.00000474923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001087276,"about_ca_system_score_gemma":0.00007680957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004886812,"about_ca_topic_score_gemma":3.510833e-7,"domain_scores_codex":[0.998834,0.0000217962,0.0005565687,0.00004244051,0.000441819,0.0001034067],"domain_scores_gemma":[0.9983628,0.00006858952,0.0007485689,0.00007590012,0.0007240686,0.00002004869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004596925,0.00001075203,0.0007108256,0.00002926698,0.00006576841,5.327332e-8,0.002965701,0.001595692,0.00004090895,0.9801341,0.0005923148,0.0138087],"study_design_scores_gemma":[0.002212865,0.0004307189,0.005346002,0.0001475788,0.00007518983,0.0000325874,0.1965892,0.03153036,0.00142927,0.05438156,0.707615,0.0002096164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05815622,0.00003636029,0.8658221,0.004747231,0.0008470684,0.0009909262,0.000008287964,0.0000217618,0.06937002],"genre_scores_gemma":[0.9786749,0.0001813773,0.02069038,0.0002216497,0.00004449309,0.00001075849,0.000002701351,0.000001657708,0.0001721016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9257525,"threshold_uncertainty_score":0.193633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01683395669448635,"score_gpt":0.3082151655254389,"score_spread":0.2913812088309525,"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."}}