{"id":"W4247470814","doi":"10.32920/ryerson.14656917.v1","title":"Semantic analysis of Twitter content","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Semantic similarity; Computer science; Explicit semantic analysis; Semantic computing; Information retrieval; Natural language processing; Closeness; Task (project management); Similarity (geometry); Semantic compression; Process (computing); Semantic grid; Semantic analysis (machine learning); Artificial intelligence; Semantic technology; Semantics (computer science); Semantic Web","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":[0.0007683841,0.0006454776,0.000383589,0.01168942,0.001228884,0.00166996,0.0003840637,0.0005188583,0.004937805],"category_scores_gemma":[0.005739058,0.00013391,0.0007943727,0.007845196,0.0006171151,0.003550076,0.001284776,0.0004580048,0.002801202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00151729,"about_ca_system_score_gemma":0.0008982465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003681479,"about_ca_topic_score_gemma":0.003887123,"domain_scores_codex":[0.9986795,0.0003191707,0.0001381927,0.0002058354,0.0005272775,0.0001299786],"domain_scores_gemma":[0.9977508,0.0006887818,0.0003975606,0.0002226101,0.0008531907,0.00008715085],"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":[0.000957624,0.0002439921,0.06334399,0.002524226,0.0003377057,0.001717099,0.006686316,0.01556196,0.04234307,0.2118221,0.09074596,0.5637159],"study_design_scores_gemma":[0.00005713386,0.0002249383,0.1251704,0.0006700325,0.0003202159,0.001606589,0.01237066,0.2220619,0.03423739,0.1871087,0.4159786,0.0001935213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3653232,0.003885206,0.3369263,0.00638836,0.001153987,0.001828767,0.1209368,0.005190382,0.158367],"genre_scores_gemma":[0.8266361,0.00212496,0.0986765,0.0004514368,0.000686285,0.001236239,0.05317966,0.000532007,0.01647684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01168942,"threshold_uncertainty_score":0.01651859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08276999196305927,"score_gpt":0.2837956206522319,"score_spread":0.2010256286891726,"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."}}