{"id":"W4386566452","doi":"10.18653/v1/2023.findings-eacl.136","title":"Best Practices in the Creation and Use of Emotion Lexicons","year":2023,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Lexicon; Set (abstract data type); Computer science; Sentiment analysis; Tracking (education); Work (physics); Emotion classification; Word (group theory); Cognitive psychology; Emotion detection; Artificial intelligence; Natural language processing; Psychology; Emotion recognition; Linguistics","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":[0.0002984811,0.00002070793,0.00003460606,0.0000862219,0.00002639767,0.0001011662,0.00008725316,0.000009662339,0.00000720518],"category_scores_gemma":[0.00007569756,0.00001323926,0.00001081814,0.0004170962,0.000009883645,0.0004700737,0.0000340277,0.00001860135,0.00001113118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001723482,"about_ca_system_score_gemma":0.000004897513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002013818,"about_ca_topic_score_gemma":0.00005437403,"domain_scores_codex":[0.9996717,0.00004479006,0.0000778244,0.00007657468,0.00008919319,0.00003990122],"domain_scores_gemma":[0.999585,0.0002079606,0.00008179598,0.00010457,0.00001476497,0.000005964375],"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":[0.000005652804,0.000211451,0.5762977,0.0000236404,0.00004693576,0.000007799053,0.0153833,0.001100665,0.00320577,0.2720268,0.00503193,0.1266584],"study_design_scores_gemma":[0.0001632825,0.00005415413,0.3978475,0.00002378865,0.00001191461,0.000002435454,0.002435645,0.5944633,0.0008744456,0.0007767768,0.003280209,0.00006652523],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805255,0.00001728884,0.01416663,0.003075316,0.00003754716,0.00004823992,1.291193e-7,0.00001881145,0.002110555],"genre_scores_gemma":[0.9965962,0.00005861868,0.00263928,0.0000673174,0.000008215461,0.000001312937,0.00000209711,6.686987e-7,0.0006263191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5933627,"threshold_uncertainty_score":0.0975548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.168320874261917,"score_gpt":0.3703668228333954,"score_spread":0.2020459485714784,"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."}}