{"id":"W1930223417","doi":"10.1109/tmm.2015.2482228","title":"Deep Multimodal Learning for Affective Analysis and Retrieval","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Modalities; Social media; Upload; Representation (politics); Multimodal learning; Artificial intelligence; Emotion classification; Feature learning; Multimodality; Information retrieval; Automatic summarization; Natural language processing; Machine learning; World Wide Web","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":[0.0004291808,0.0001648308,0.000279028,0.0005167006,0.0002206975,0.0001284485,0.0002187839,0.00008610006,0.00001991573],"category_scores_gemma":[0.00004562674,0.0001557503,0.0002384775,0.001025784,0.00004828595,0.0003218818,0.000003495432,0.0001936383,0.00002817064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005739723,"about_ca_system_score_gemma":0.00003433425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715533,"about_ca_topic_score_gemma":0.00005462437,"domain_scores_codex":[0.9986748,0.00009890841,0.0002113662,0.000467853,0.0002963596,0.0002507501],"domain_scores_gemma":[0.998825,0.0004568756,0.0000885302,0.0002499122,0.0001560403,0.0002236511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003422944,0.0004910703,0.003329221,0.00001840036,0.002787765,0.00001056774,0.0125411,0.5112841,0.002580618,0.0001097665,0.0001235438,0.4663816],"study_design_scores_gemma":[0.001129043,0.0001856019,0.001064934,0.000004979604,0.0003151241,0.000001502277,0.0002497047,0.9875225,0.009158101,0.00003700822,0.0001468834,0.0001846389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02448811,0.00005393453,0.9745303,0.0001348123,0.0004072646,0.0001945174,0.000002670305,0.0001189243,0.00006940324],"genre_scores_gemma":[0.897568,0.00001468492,0.1019888,0.00004625956,0.00005258156,0.00002281706,0.000006304282,0.00001059722,0.000289899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8730799,"threshold_uncertainty_score":0.6351311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02515312700733929,"score_gpt":0.2826347932597046,"score_spread":0.2574816662523653,"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."}}