{"id":"W4285040144","doi":"10.22215/etd/2022-15019","title":"Unsupervised Text Mining Techniques for Forecasting Crude Oil","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Artificial intelligence; Crude oil; Transformer; Sentiment analysis; Natural language processing; Encoder; Machine learning; Econometrics; Economics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008424814,0.0006291991,0.0005015755,0.002905257,0.0004102048,0.0005801384,0.0005536109,0.0004664529,0.001245936],"category_scores_gemma":[0.003704663,0.0001800206,0.0007818554,0.002537583,0.000152198,0.0008645621,0.0002449621,0.0006611084,0.0008426025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003657457,"about_ca_system_score_gemma":0.0007160655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003427312,"about_ca_topic_score_gemma":0.005297855,"domain_scores_codex":[0.9995235,0.0001359068,0.00007303413,0.00009272855,0.0001448584,0.00002990745],"domain_scores_gemma":[0.99777,0.001519168,0.00019486,0.0001242297,0.0003650184,0.00002682814],"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":[0.0001648354,0.0005508196,0.01474555,0.0004297737,0.0002311601,0.0003273073,0.000223304,0.1189064,0.01902066,0.007943686,0.01099485,0.8264616],"study_design_scores_gemma":[0.00003193173,0.00009319336,0.008406911,0.00004739319,0.00005473828,0.0001279401,0.0001212204,0.9614735,0.008523184,0.01180147,0.009296067,0.00002247451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1255466,0.002782044,0.8514397,0.001446241,0.0002350893,0.00052787,0.007675524,0.003185585,0.007161465],"genre_scores_gemma":[0.3978128,0.002069828,0.5849469,0.0001641004,0.000364957,0.000572379,0.008962168,0.0001205657,0.004986309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003427312,"threshold_uncertainty_score":0.006814778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04631743381807039,"score_gpt":0.2590781692361266,"score_spread":0.2127607354180562,"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."}}