{"id":"W4393018768","doi":"10.1049/cit2.12300","title":"GP‐FMLNet: A feature matrix learning network enhanced by glyph and phonetic information for Chinese sentiment analysis","year":2024,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Glyph (data visualization); Computer science; Feature (linguistics); Artificial intelligence; Sentiment analysis; Natural language processing; Pattern recognition (psychology); Visualization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005230628,0.001024937,0.0005646217,0.000842054,0.0004535622,0.0005079173,0.00112251,0.0008477854,0.002445889],"category_scores_gemma":[0.00147576,0.000287837,0.0006386915,0.0008642985,0.0002948284,0.001098336,0.0007766385,0.001084194,0.0008545439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007427828,"about_ca_system_score_gemma":0.0006451882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01014883,"about_ca_topic_score_gemma":0.009098071,"domain_scores_codex":[0.9998006,0.00004142822,0.00001108979,0.0000675649,0.00004377237,0.0000356169],"domain_scores_gemma":[0.999745,0.00009087583,0.00002271911,0.00002377523,0.0001000884,0.00001749803],"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":[0.000386107,0.0002784084,0.00409099,0.0001549988,0.0001526823,0.0002358656,0.0001211698,0.1750679,0.01446116,0.002525244,0.01789038,0.7846351],"study_design_scores_gemma":[0.00001260465,0.00004916266,0.0004079473,0.000005375697,0.00001631799,0.00001367516,0.00001133687,0.9960376,0.001426807,0.00111902,0.0008941561,0.00000594838],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1812319,0.001293002,0.7994212,0.001152136,0.000484666,0.0002913594,0.001437943,0.008259852,0.006427873],"genre_scores_gemma":[0.8068009,0.0005347095,0.1777318,0.0007272496,0.0002458247,0.0003009872,0.003521906,0.0002006307,0.009935955],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01014883,"threshold_uncertainty_score":0.02017951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004678158519829099,"score_gpt":0.269678636448601,"score_spread":0.2650004779287718,"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."}}