{"id":"W2773991511","doi":"10.26615/978-954-452-049-6_094","title":"Multi-entity sentiment analysis using entity-level feature extraction and word embeddings approach","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Sentiment analysis; Natural language processing; Lexicon; Artificial intelligence; Word (group theory); Task (project management); String (physics); Feature (linguistics); Polarity (international relations); Relation (database); Binary classification; Linguistics; Data mining; Mathematics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005379936,0.0001950327,0.0003232188,0.0003732063,0.001054708,0.00207458,0.0006797633,0.00009617893,0.00006610585],"category_scores_gemma":[0.00003014252,0.0001740505,0.0002573439,0.0004427828,0.00006050393,0.001636424,0.0005419079,0.0001598314,0.00001237914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005199548,"about_ca_system_score_gemma":0.00001826343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003369264,"about_ca_topic_score_gemma":0.00007730786,"domain_scores_codex":[0.9983469,0.00005439458,0.0002381677,0.0006823617,0.0003942693,0.0002839241],"domain_scores_gemma":[0.9984614,0.00002184642,0.00035457,0.0009331278,0.0001000261,0.0001290394],"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":[0.00002640644,0.001387254,0.8898352,0.00009401615,0.006469145,0.0000401396,0.003202038,0.003745703,0.03026226,0.00929776,0.003058497,0.05258153],"study_design_scores_gemma":[0.0003200322,0.000005635767,0.1721296,0.000008210763,0.0003765204,0.000005341594,0.0001367602,0.8252335,0.00115818,0.00003075336,0.0003745127,0.0002210091],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1787671,0.00008233303,0.8197297,0.0002029593,0.0002297134,0.00009750672,0.000001836826,0.00005881303,0.0008300508],"genre_scores_gemma":[0.5693603,0.00001936155,0.4265172,0.00004567207,0.00005417756,0.000002817711,0.000008126115,0.000005709047,0.003986581],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8214878,"threshold_uncertainty_score":0.9989614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08222425526620293,"score_gpt":0.3446523552865046,"score_spread":0.2624281000203017,"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."}}