{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005375565,0.001480563,0.001365379,0.00747251,0.00107485,0.002645059,0.002279222,0.001810479,0.001778378],"category_scores_gemma":[0.01239149,0.0004490967,0.001639832,0.003819257,0.002438277,0.00371774,0.002279427,0.001885936,0.001584248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001299941,"about_ca_system_score_gemma":0.001160986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00158061,"about_ca_topic_score_gemma":0.001867554,"domain_scores_codex":[0.9904423,0.005000432,0.0005592805,0.00160864,0.002142758,0.0002465355],"domain_scores_gemma":[0.9815053,0.01025221,0.001972436,0.002451085,0.003464676,0.0003542993],"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":[0.000432499,0.001147165,0.006029953,0.0009107896,0.0004300953,0.0004026397,0.00144399,0.1285382,0.01977439,0.03815074,0.01276736,0.7899721],"study_design_scores_gemma":[0.00002041894,0.00006580976,0.001518946,0.00005677448,0.0000324479,0.0001355688,0.000252802,0.9270403,0.007983442,0.05776656,0.00508317,0.00004363028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01370253,0.0004024572,0.9823403,0.0003564712,0.00007146792,0.0001980323,0.0002213083,0.001107452,0.001599846],"genre_scores_gemma":[0.2505307,0.0003587266,0.7436503,0.0002845029,0.0003084147,0.0005171366,0.001377041,0.0002364501,0.002736733],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00747251,"threshold_uncertainty_score":0.02842903,"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."}}