{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004189835,0.0002648667,0.0002487013,0.0002117742,0.0004945435,0.00009629229,0.001038704,0.000184066,0.00007328389],"category_scores_gemma":[0.00007635641,0.0003306513,0.00008490251,0.0002913954,0.0001026835,0.0005214546,0.002335425,0.0004548626,0.00002497826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386632,"about_ca_system_score_gemma":0.0006686766,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03360851,"about_ca_topic_score_gemma":0.08217494,"domain_scores_codex":[0.9978026,0.0001236581,0.0002917335,0.001198947,0.0002512455,0.0003317789],"domain_scores_gemma":[0.9979626,0.0001078131,0.0004011172,0.001074707,0.0002232479,0.0002305219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002129627,0.000543777,0.1630068,0.002216391,0.002284453,0.001781423,0.01170825,0.4531915,0.002498277,0.2708441,0.0759762,0.015736],"study_design_scores_gemma":[0.0006063613,0.00001533072,0.01154583,0.0003662391,0.0001057641,0.00001550263,0.0002862465,0.9646277,0.0001342923,0.008092678,0.01357754,0.0006265435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4893028,0.00006789165,0.5035712,0.0005949303,0.001481705,0.0002936942,0.00001874073,0.0002275555,0.004441459],"genre_scores_gemma":[0.9925396,0.00009975474,0.003922484,0.0001167226,0.0001290461,0.000002109977,0.00003753139,0.00001528321,0.003137402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5114362,"threshold_uncertainty_score":0.9999145,"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."}}