{"id":"W4304806684","doi":"10.1007/s11634-022-00522-6","title":"On smoothing and scaling language model for sentiment based information retrieval","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Sentiment analysis; Latent Dirichlet allocation; Relevance (law); Social media; Smoothing; Probabilistic logic; Field (mathematics); Information retrieval; Language model; Artificial intelligence; Dirichlet distribution; Topic model; Data mining; World Wide Web; 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":[],"consensus_categories":[],"category_scores_codex":[0.0008255333,0.00007340954,0.0001394743,0.0004015766,0.000233189,0.0001599538,0.0003598009,0.00001616117,0.000007489708],"category_scores_gemma":[0.00005288199,0.00007178403,0.00003578321,0.0007872966,0.00001458067,0.001450739,0.0002165784,0.00006804402,5.185686e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003755178,"about_ca_system_score_gemma":0.00001573389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006069756,"about_ca_topic_score_gemma":0.00001421091,"domain_scores_codex":[0.9989925,0.00004885557,0.0002708233,0.0003349465,0.0002486911,0.0001041514],"domain_scores_gemma":[0.9991204,0.0001233151,0.0001833862,0.0005210144,0.00002369136,0.00002817746],"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":[0.000123884,0.0001871853,0.008549796,0.0000627125,0.0002468012,0.000001014681,0.003683811,0.5996198,0.001057728,0.07212351,0.0002699586,0.3140738],"study_design_scores_gemma":[0.0002594739,0.00001465704,0.001255438,0.000004896778,0.00008295556,1.38834e-7,0.0004977383,0.9961899,0.0000608475,0.0004906481,0.001057468,0.00008583856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02241561,0.0004087288,0.9763814,0.0005250829,0.00003396491,0.0001048299,0.0000525027,0.00001748042,0.0000604553],"genre_scores_gemma":[0.9647059,0.0001250059,0.03361324,0.0002742678,0.000008015204,0.00002025254,0.001226386,0.00000255711,0.00002433719],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9427681,"threshold_uncertainty_score":0.2927268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03478667359186854,"score_gpt":0.3244483637770839,"score_spread":0.2896616901852153,"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."}}