{"id":"W4250013712","doi":"10.32920/ryerson.14656917","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; Information retrieval; Semantic computing; Natural language processing; Closeness; Task (project management); Similarity (geometry); Process (computing); Semantic compression; Semantic analysis (machine learning); Artificial intelligence; Semantic grid; Semantics (computer science); Semantic technology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002969491,0.0001718829,0.0007675202,0.0006356053,0.00002380581,0.0002582269,0.001360692,0.0001128154,0.0002766297],"category_scores_gemma":[0.00004125341,0.000142264,0.0007123044,0.001343333,0.00002980595,0.0001032053,0.002404233,0.0002012695,0.00001115452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001870247,"about_ca_system_score_gemma":0.00009531654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009898908,"about_ca_topic_score_gemma":0.0001164224,"domain_scores_codex":[0.9982843,0.00008469649,0.0004367719,0.0006726443,0.0003546983,0.0001668757],"domain_scores_gemma":[0.997449,0.00006645941,0.0002425017,0.001954126,0.0002230591,0.00006484989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002226804,0.003173293,0.3621357,0.002116406,0.2437265,0.001181552,0.02686184,0.1250487,0.02273511,0.03521491,0.05464016,0.1231436],"study_design_scores_gemma":[0.000146226,0.00002040042,0.04176759,0.0001190498,0.005866504,0.000002379665,0.0004182729,0.9477705,0.002834144,0.0001440454,0.0003595169,0.0005514115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1857636,0.0001830471,0.8111371,0.0008442936,0.0001891022,0.00003584794,0.00001264365,0.00006633916,0.001767962],"genre_scores_gemma":[0.9534035,0.00004107916,0.04439888,0.000457263,0.00002134243,0.000005694043,0.0001737109,0.000004861836,0.00149364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8227218,"threshold_uncertainty_score":0.5801357,"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."}}