{"id":"W2609579487","doi":"10.1007/s11280-017-0460-2","title":"Collaborative text categorization via exploiting sparse coefficients","year":2017,"lang":"en","type":"article","venue":"World Wide Web","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Sparse approximation; Pattern recognition (psychology); Categorization; Artificial intelligence; Classifier (UML); Sparse matrix; Representation (politics); Information retrieval; Data mining","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":[0.000180381,0.0001310135,0.0001331556,0.0001945851,0.0007185917,0.0007188632,0.001409987,0.00004425931,0.00003299072],"category_scores_gemma":[0.0002713512,0.0001241996,0.00003082716,0.0004714935,0.0001313225,0.001019404,0.0003947787,0.0001075505,0.0003174217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006153612,"about_ca_system_score_gemma":0.0000763657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001744491,"about_ca_topic_score_gemma":0.0001076875,"domain_scores_codex":[0.998906,0.00003104236,0.0002125517,0.0003666638,0.0002404985,0.0002432525],"domain_scores_gemma":[0.9983078,0.00007460759,0.0003229534,0.001093861,0.0001461854,0.00005460116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001251943,0.0001837013,0.04214465,0.00001737512,0.00003314676,0.00002358771,0.001110046,0.0002077654,0.01168314,0.651364,0.02749866,0.2657214],"study_design_scores_gemma":[0.002493059,0.0001740699,0.09498329,0.0001616374,0.00003188891,0.000007934374,0.0009252041,0.1570261,0.134213,0.05507298,0.5532948,0.001616104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02720687,0.0001291291,0.9164581,0.01326913,0.001245641,0.0004592788,0.000005538569,0.001342671,0.03988361],"genre_scores_gemma":[0.987865,0.00001582687,0.007503513,0.0001875354,0.00003861269,0.00003819998,0.000005017593,0.000009036043,0.004337231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606581,"threshold_uncertainty_score":0.6932015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01904446666712901,"score_gpt":0.2666869600097453,"score_spread":0.2476424933426163,"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."}}