{"id":"W1569507287","doi":"10.1111/coin.12024","title":"Using Hashtags to Capture Fine Emotion Categories from Tweets","year":2014,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":412,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Lexicon; Social media; Computer science; Emotion classification; Sentiment analysis; Big Five personality traits; Word (group theory); Microblogging; Admiration; Natural language processing; Artificial intelligence; Emotion detection; Personality; Psychology; Emotion recognition; Linguistics; Social psychology; World Wide 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":[0.0001973091,0.0001381531,0.0001624932,0.0001496124,0.0001643399,0.0002342863,0.0005443624,0.0000441646,0.00009610151],"category_scores_gemma":[0.00007588007,0.0001347817,0.00006966509,0.0005128829,0.00003042899,0.0003100786,0.0001768972,0.00008474543,0.0002635564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004207456,"about_ca_system_score_gemma":0.00004294517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001798384,"about_ca_topic_score_gemma":0.00001624441,"domain_scores_codex":[0.998681,0.000063317,0.0002923652,0.0004183052,0.00036128,0.0001837142],"domain_scores_gemma":[0.9990798,0.0002333894,0.000102185,0.000259231,0.0002151085,0.0001102511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003571844,0.00003358218,0.001764902,0.000003525105,0.00002843663,0.000002187335,0.001698946,0.8799006,0.0002983691,0.08247226,0.0006458497,0.0331478],"study_design_scores_gemma":[0.00003876674,0.00002441688,0.003687653,0.00002607241,0.000007652896,0.000002769915,0.00006658957,0.9491493,0.001767894,0.04410637,0.0009520356,0.0001705378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04487142,0.00007955726,0.9533576,0.0007448538,0.0005074251,0.00006419532,0.000002884675,0.0000717099,0.0003003041],"genre_scores_gemma":[0.7442498,8.246187e-7,0.255022,0.0004759918,0.0001364094,0.0000021266,0.00003324643,0.000005575652,0.00007395504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6993784,"threshold_uncertainty_score":0.5496238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06287620001503862,"score_gpt":0.3180379788060219,"score_spread":0.2551617787909832,"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."}}