{"id":"W1999247825","doi":"10.1016/j.ipm.2009.06.005","title":"Facet-based opinion retrieval from blogs","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Facet (psychology); Query expansion; Lexicon; Structuring; Divergence (linguistics); Natural language processing; Artificial intelligence; Linguistics","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":[0.0002257256,0.0001100049,0.00008869886,0.0001640723,0.0001421933,0.0005519463,0.0005505629,0.0000423991,0.00001031625],"category_scores_gemma":[0.00001305623,0.0001077488,0.00002963864,0.000308268,0.000009488719,0.0025844,0.00008658188,0.00008144523,0.0001075442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006942105,"about_ca_system_score_gemma":0.00003756217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005312315,"about_ca_topic_score_gemma":1.385213e-7,"domain_scores_codex":[0.9988763,0.0000139472,0.0003444242,0.0001676406,0.0004079741,0.0001897123],"domain_scores_gemma":[0.9993401,0.000007209716,0.0001718708,0.0003572645,0.00007531748,0.0000482438],"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":[0.000007002719,0.00002259167,0.00001621905,0.00005225754,0.000005281896,0.000001195609,0.0007892608,0.007372029,0.00002424638,0.01262913,0.0006324112,0.9784484],"study_design_scores_gemma":[0.0006889086,0.00003416386,0.003229827,0.00012713,0.00000617664,7.566381e-7,0.0001005562,0.9566913,0.0007211014,0.009700712,0.0284753,0.0002241126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003487233,0.00005675211,0.9816833,0.002438658,0.0002763593,0.0001790232,0.000001036486,0.0003570582,0.01152057],"genre_scores_gemma":[0.8463968,0.000006646708,0.1496321,0.003815664,0.00004447805,0.00000515705,0.00002994625,0.000002643285,0.00006655801],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9782243,"threshold_uncertainty_score":0.5322431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596783699014856,"score_gpt":0.2525663967330099,"score_spread":0.2365985597428613,"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."}}