{"id":"W2783366437","doi":"10.1109/bigdata.2017.8258136","title":"Semi-supervised learning and social media text analysis towards multi-labeling categorization","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; WordNet; Categorization; Machine learning; Natural language processing; Supervised learning; Annotation; Graph; Task (project management); Labeled data; Pattern recognition (psychology); Artificial neural network","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":[0.0002030554,0.00009660715,0.0001524073,0.0001893726,0.0008253062,0.0007566586,0.0006636632,0.00009091617,0.00003617425],"category_scores_gemma":[0.0002352608,0.00008411642,0.00004877513,0.0002498883,0.00008636577,0.0007047122,0.0003654137,0.0001117881,0.00001795089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002112758,"about_ca_system_score_gemma":0.00002354415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005517941,"about_ca_topic_score_gemma":0.00006384354,"domain_scores_codex":[0.9991754,0.0000264806,0.0001561298,0.0003079579,0.0001750251,0.0001589717],"domain_scores_gemma":[0.9993626,0.00004288301,0.0001429255,0.0003388512,0.00008124235,0.00003149938],"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":[0.000002822985,0.00005330188,0.06006273,0.00001333547,0.0001724075,0.000002749266,0.004967841,0.00005179538,0.006365461,0.1034715,0.0001200754,0.824716],"study_design_scores_gemma":[0.0008960271,0.00002481974,0.1702735,0.000004584783,0.0001302104,0.000001059661,0.00182565,0.8114092,0.01008797,0.002720324,0.002183818,0.0004428708],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05270782,0.00005379179,0.9411021,0.003925411,0.000114094,0.00006420247,6.700206e-7,0.0006387098,0.001393195],"genre_scores_gemma":[0.9702652,0.00005528078,0.02887044,0.00003252391,0.00002533221,0.000007606841,0.00000828854,0.000004243404,0.0007310997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9175574,"threshold_uncertainty_score":0.7296476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0454807030774755,"score_gpt":0.2997944648698337,"score_spread":0.2543137617923582,"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."}}