{"id":"W1967097654","doi":"10.1007/s13278-014-0193-5","title":"Predicting political preference of Twitter users","year":2014,"lang":"en","type":"article","venue":"Social Network Analysis and Mining","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Preference; Computer science; Variety (cybernetics); Context (archaeology); Politics; Sentiment analysis; Artificial intelligence; Work (physics); Natural language processing; Information retrieval; Political science; Law; Mathematics; Statistics","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":[0.0006280035,0.0001152886,0.0003969531,0.0001631127,0.0002554681,0.0001051736,0.0002647441,0.00006483711,0.00001929486],"category_scores_gemma":[0.0000360949,0.0001054346,0.0002226936,0.001188014,0.00006688297,0.0001400527,0.0001787556,0.00008028536,0.000001282846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001048295,"about_ca_system_score_gemma":0.00001432501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005618557,"about_ca_topic_score_gemma":0.00002905493,"domain_scores_codex":[0.9985821,0.0001277929,0.0003465275,0.0003212652,0.0002518663,0.0003704341],"domain_scores_gemma":[0.9992713,0.0001823224,0.000196206,0.0001873533,0.00006743297,0.00009534037],"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":[0.0000034499,0.00001971739,0.8759153,0.000008956733,0.0008325224,5.744729e-7,0.002332422,0.0007575373,0.00003677394,0.1069668,0.0002512371,0.01287467],"study_design_scores_gemma":[0.000369724,0.00007669102,0.2579931,0.00004305788,0.001175032,7.637659e-7,0.001189678,0.7345226,0.00009453687,0.003461838,0.0007289563,0.0003439996],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6911589,0.0000813361,0.3046686,0.0003479381,0.00009542632,0.00003229985,5.080854e-7,0.00004010172,0.003574895],"genre_scores_gemma":[0.9839324,0.000006780201,0.01539265,0.0002124903,0.0003603698,0.000002327096,0.000005162406,0.000004759169,0.00008303498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7337651,"threshold_uncertainty_score":0.4299498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02924801817375477,"score_gpt":0.2670297265927906,"score_spread":0.2377817084190358,"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."}}