{"id":"W4379385814","doi":"10.14569/ijacsa.2023.0140505","title":"An Enhanced SVM Model for Implicit Aspect Identification in Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Advanced Computer Science and Applications","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Overfitting; Computer science; Support vector machine; WordNet; Sentiment analysis; Artificial intelligence; Machine learning; Benchmark (surveying); Identification (biology); Kernel (algebra); Task (project management); Artificial neural network","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":[0.0008791366,0.0006650013,0.0007794868,0.0005381628,0.000297896,0.0009429932,0.0009794912,0.0008269551,0.001907606],"category_scores_gemma":[0.002062962,0.0002680969,0.0007466662,0.0005694314,0.0002189482,0.001311675,0.000535765,0.00124345,0.001179048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004808162,"about_ca_system_score_gemma":0.0006646138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002924724,"about_ca_topic_score_gemma":0.002570249,"domain_scores_codex":[0.9995845,0.0001113387,0.00004684568,0.0001056076,0.0000977189,0.00005407225],"domain_scores_gemma":[0.9992023,0.000271838,0.00006394161,0.00005363775,0.0003780949,0.00003021016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005100184,0.0003889543,0.00814089,0.000227007,0.0001675547,0.0002258897,0.0002284016,0.4052774,0.02169851,0.008011696,0.00695768,0.548166],"study_design_scores_gemma":[0.000003277463,0.0000188637,0.0002336617,0.000003691669,0.000007114792,0.00001161917,0.000005499342,0.9980925,0.0004844903,0.0008002894,0.0003365039,0.000002486528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0741336,0.0006061136,0.9206919,0.0004855304,0.0001572537,0.00009774772,0.0002572096,0.001301656,0.002269052],"genre_scores_gemma":[0.8258822,0.0003747079,0.1676696,0.0002816068,0.0001562305,0.0001889079,0.0009658145,0.0001049642,0.00437589],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002924724,"threshold_uncertainty_score":0.006381631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01869574222535429,"score_gpt":0.3463898390964029,"score_spread":0.3276940968710486,"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."}}