{"id":"W3197264270","doi":"10.1016/j.knosys.2021.107449","title":"Enhancing emotion inference in conversations with commonsense knowledge","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Conversation; Computer science; Inference; Commonsense knowledge; Utterance; Leverage (statistics); Commonsense reasoning; Feeling; Knowledge graph; Task (project management); Natural language processing; Artificial intelligence; Cognitive psychology; Knowledge base; Psychology; Social psychology; Communication","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":[0.0006262143,0.0001992061,0.0003580507,0.000360664,0.0001713136,0.0003128034,0.0003539719,0.00008307787,0.00002932452],"category_scores_gemma":[0.0001243981,0.000183305,0.00008776475,0.001648594,0.00004366685,0.0002931306,0.00009916221,0.0001733747,0.0002602625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611474,"about_ca_system_score_gemma":0.0006573528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009134472,"about_ca_topic_score_gemma":0.001638765,"domain_scores_codex":[0.9979622,0.0004874013,0.0004901506,0.0005150387,0.0002279984,0.000317254],"domain_scores_gemma":[0.9979245,0.0006701529,0.0001615326,0.0006691563,0.0004580875,0.0001165675],"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":[0.0001255127,0.006131438,0.5315582,0.002603787,0.0008233768,0.0008786512,0.0718643,0.07587172,0.05144227,0.2253309,0.004989563,0.02838035],"study_design_scores_gemma":[0.001926827,0.0001081998,0.00742434,0.001329766,0.00003586992,0.00001735092,0.002013521,0.9635688,0.01783733,0.00004787772,0.005139802,0.0005503321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1366019,0.002197548,0.8514297,0.0003172918,0.001232479,0.0002816105,0.000003022781,0.0001928441,0.007743556],"genre_scores_gemma":[0.9960836,0.000005967956,0.002616132,0.00003653263,0.00009277881,0.00003401269,0.00002639653,0.00001281929,0.00109174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.887697,"threshold_uncertainty_score":0.7474961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02968138502428072,"score_gpt":0.2835319008581277,"score_spread":0.253850515833847,"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."}}