{"id":"W3185093711","doi":"","title":"Hashtag Politics: A Twitter sentiment analysis of the 2015 Canadian Federal Election","year":2016,"lang":"en","type":"article","venue":"URSCA Proceedings","topic":"Social Media and Politics","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"MacEwan University","funders":"","keywords":"Sentiment analysis; Social media; Federal election; General election; Reputation; Politics; Democracy; Political science; Lexicon; Government (linguistics); Advertising; Public relations; Computer science; Artificial intelligence; Business; Law; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000889977,0.0004336408,0.0003386461,0.002638613,0.002013005,0.0009583585,0.0004010419,0.000233523,0.003369447],"category_scores_gemma":[0.00276996,0.0001400018,0.0003013926,0.003497941,0.0003993463,0.0004302239,0.0005189681,0.0004180954,0.0009667551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008335503,"about_ca_system_score_gemma":0.008349846,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8879642,"about_ca_topic_score_gemma":0.9509212,"domain_scores_codex":[0.9992474,0.00006557361,0.0000248845,0.0000825947,0.0004208986,0.0001586459],"domain_scores_gemma":[0.9983797,0.0001823968,0.0001199703,0.0000491688,0.001109248,0.0001594641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001337241,0.0004367727,0.6649407,0.000510828,0.0001623867,0.000389226,0.008680771,0.004657998,0.02272278,0.003223284,0.08337454,0.2095634],"study_design_scores_gemma":[0.00001839412,0.00008494021,0.9574481,0.00003183457,0.00004335315,0.00003482962,0.004424183,0.008892593,0.002528437,0.0002425726,0.02619667,0.00005409545],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9488556,0.0001671173,0.002405658,0.0005158589,0.00009773279,0.0004330004,0.03124993,0.0003770305,0.01589805],"genre_scores_gemma":[0.9488953,0.0002253436,0.007306781,0.0001470864,0.00005426633,0.0003697663,0.02875751,0.0001127312,0.01413112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1120358,"threshold_uncertainty_score":0.225391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01896787996672229,"score_gpt":0.2991133409167496,"score_spread":0.2801454609500273,"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."}}