{"id":"W2583888098","doi":"10.1109/icdmw.2016.0139","title":"Multi-sentiment Modeling with Scalable Systematic Labeled Data Generation via Word2Vec Clustering","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Word2vec; Computer science; Sentiment analysis; Scalability; Cluster analysis; Emoji; Social media; Classifier (UML); Binary classification; Artificial intelligence; Machine learning; Big data; Data mining; Data science; World Wide Web; Support vector machine","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":[0.0008417777,0.001281623,0.0007475367,0.000804243,0.0005606643,0.0007973508,0.001457149,0.0008761691,0.001847658],"category_scores_gemma":[0.003263589,0.0006225499,0.001095227,0.000898048,0.0003615582,0.001225171,0.00095829,0.001412279,0.001889685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008001556,"about_ca_system_score_gemma":0.001156453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01146071,"about_ca_topic_score_gemma":0.02114054,"domain_scores_codex":[0.9993969,0.0001659854,0.00004083243,0.0001920294,0.0001233264,0.00008083318],"domain_scores_gemma":[0.9987419,0.0004114256,0.00007974366,0.0001893089,0.0005370026,0.00004064418],"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":[0.0004245446,0.0005064028,0.00701398,0.0002653151,0.0002311429,0.0002933861,0.0004041033,0.4430918,0.02444484,0.005209227,0.04038633,0.4777289],"study_design_scores_gemma":[0.0000142886,0.00002641025,0.000295227,0.000004407061,0.000007159924,0.00001246623,0.00002866464,0.9941497,0.002640477,0.001919828,0.0008936806,0.000007814328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07918423,0.0002940898,0.9024179,0.0005277823,0.0003396848,0.0003998372,0.003051169,0.01142904,0.002356194],"genre_scores_gemma":[0.4289508,0.0002024728,0.5491069,0.000505687,0.0001540613,0.0009186009,0.01585849,0.0007525508,0.003550429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01146071,"threshold_uncertainty_score":0.02278805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09569589603432707,"score_gpt":0.2842106160174,"score_spread":0.1885147199830729,"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."}}