{"id":"W3105333265","doi":"10.48550/arxiv.1906.02331","title":"OutdoorSent: Sentiment Analysis of Urban Outdoor Images by Using Semantic and Deep Features","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Sentiment analysis; Generalization; Context (archaeology); Artificial intelligence; Information retrieval; Data science; Machine learning; Geography","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":[0.0001654,0.0001555651,0.0003551726,0.0004839186,0.00008681371,0.00008082623,0.0004223837,0.00005445224,0.00007550504],"category_scores_gemma":[0.000005818911,0.0001592003,0.000220486,0.001547764,0.0000472768,0.0003864939,0.0002709909,0.0000737452,0.00001619718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003739489,"about_ca_system_score_gemma":0.00001447354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001231309,"about_ca_topic_score_gemma":0.00001331652,"domain_scores_codex":[0.998852,0.00007042876,0.000178518,0.0005582573,0.0001171288,0.0002236596],"domain_scores_gemma":[0.9990792,0.00006099673,0.0002004639,0.0004944169,0.00007135889,0.00009358759],"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":[0.00002238898,0.0001822289,0.9303566,0.00004071635,0.002727939,0.00003950067,0.0008933962,0.04022172,0.00870436,0.01532389,0.000650937,0.0008363053],"study_design_scores_gemma":[0.0004352959,0.00003558749,0.0197563,0.00001812017,0.0009414948,9.637005e-7,0.000397061,0.9753045,0.002637006,0.0001031057,0.0001287594,0.0002417769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8915662,0.0002879927,0.1075484,0.00003606163,0.00009485248,0.00008651677,0.000004590162,0.00003323265,0.0003421191],"genre_scores_gemma":[0.9971003,0.00004720409,0.000976422,0.00004323964,0.000009687863,6.302161e-8,0.000008174268,0.000006037812,0.0018089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9350828,"threshold_uncertainty_score":0.6492001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02521259281786398,"score_gpt":0.1880397882316355,"score_spread":0.1628271954137716,"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."}}