{"id":"W1589554437","doi":"10.48550/arxiv.1308.6242","title":"NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Lexicon; Sentiment analysis; Task (project management); Word (group theory); Variety (cybernetics); Natural language processing; Term (time); Artificial intelligence; State (computer science); Information retrieval; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007571367,0.002286258,0.001488346,0.006824818,0.003224473,0.003920916,0.003286567,0.001434833,0.01315561],"category_scores_gemma":[0.01567723,0.001161536,0.001787228,0.0042533,0.00112736,0.004669303,0.003551071,0.002756419,0.01464532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008288885,"about_ca_system_score_gemma":0.02250096,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.7050651,"about_ca_topic_score_gemma":0.7127748,"domain_scores_codex":[0.9939033,0.001130539,0.0002796713,0.001176082,0.002938432,0.0005718694],"domain_scores_gemma":[0.9860761,0.001527004,0.0002833704,0.001320429,0.009995261,0.0007979293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007349603,0.000327977,0.01383351,0.0009111307,0.0003071688,0.000231171,0.001063514,0.005959657,0.02665848,0.006746707,0.2567023,0.6865234],"study_design_scores_gemma":[0.0003673373,0.0004240167,0.02543899,0.0006278061,0.0004246709,0.0002984308,0.002270771,0.4438404,0.04699035,0.01183543,0.4670581,0.0004236014],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0783383,0.01028157,0.5904223,0.007668769,0.002614113,0.00347652,0.06057868,0.1624863,0.08413352],"genre_scores_gemma":[0.1501369,0.004005422,0.7076055,0.001449909,0.000390358,0.001345284,0.08338673,0.009496625,0.04218323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7050651,"threshold_uncertainty_score":0.5933437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02929141363701235,"score_gpt":0.1701409945858029,"score_spread":0.1408495809487905,"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."}}