{"id":"W4301054811","doi":"10.48550/arxiv.1805.04558","title":"NRC-Canada at SMM4H Shared Task: Classifying Tweets Mentioning Adverse\\n Drug Reactions and Medication Intake","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Lexicon; Task (project management); Class (philosophy); Computer science; Domain (mathematical analysis); Variety (cybernetics); Natural language processing; Artificial intelligence; Support vector machine; Word (group theory); Social media; Sentiment analysis; World Wide Web; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007520223,0.003444652,0.002530773,0.003502112,0.005892308,0.004028366,0.00278427,0.003797023,0.02901956],"category_scores_gemma":[0.02227361,0.0008772764,0.001825978,0.003420574,0.001413304,0.002867652,0.005026067,0.003277851,0.0248978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006898263,"about_ca_system_score_gemma":0.01852383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4383642,"about_ca_topic_score_gemma":0.6256918,"domain_scores_codex":[0.9941355,0.001338551,0.0002704513,0.00126111,0.002110776,0.0008835663],"domain_scores_gemma":[0.9821454,0.003480727,0.0004683971,0.003289662,0.007856799,0.002758894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006947744,0.0002919621,0.004878797,0.0004650548,0.0001339908,0.000201164,0.000416929,0.001876358,0.003965717,0.0008610915,0.930045,0.05616907],"study_design_scores_gemma":[0.0009167154,0.0004691287,0.04334613,0.0002858764,0.0002448383,0.0002598948,0.002344657,0.06633139,0.019226,0.005584118,0.8605822,0.00040887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.08969929,0.002762415,0.04755015,0.0145953,0.00865768,0.003485819,0.7290923,0.05510604,0.04905096],"genre_scores_gemma":[0.1042463,0.0007502708,0.07639511,0.002162582,0.001282445,0.002110005,0.7420117,0.004675517,0.06636597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4383642,"threshold_uncertainty_score":0.8716254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06374858205544988,"score_gpt":0.1894691382806405,"score_spread":0.1257205562251907,"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."}}